From 73a7cf596bd1ebc3bd0c9674a21072f9eaf4cc57 Mon Sep 17 00:00:00 2001
From: dyyzhmm <dyyzhmm@163.com>
Date: 星期四, 16 三月 2023 15:24:56 +0800
Subject: [PATCH] Merge pull request #3 from alibaba-damo-academy/main
---
egs/aishell/data2vec_transformer_finetune/run.sh | 2
egs_modelscope/speaker_diarization/speech_diarization_eend-ola-en-us-callhome-8k/infer.py | 10
funasr/torch_utils/load_pretrained_model.py | 10
egs/aishell/paraformerbert/run.sh | 2
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/infer.py | 13
funasr/train/trainer.py | 36 +-
setup.py | 4
egs/callhome/diarization/sond/unit_test.py | 8
egs/alimeeting/diarization/sond/infer_alimeeting_test.py | 2
egs/aishell/conformer/run.sh | 2
egs/aishell/transformer/run.sh | 2
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/README.md | 2
funasr/bin/asr_inference_paraformer.py | 2
funasr/bin/asr_inference_uniasr_vad.py | 2
funasr/runtime/onnxruntime/src/Audio.cpp | 5
egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py | 2
funasr/bin/asr_inference_paraformer_vad_punc.py | 2
tests/test_asr_inference_pipeline.py | 2
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/infer.py | 13
egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py | 2
funasr/bin/sond_inference.py | 2
funasr/bin/asr_inference_mfcca.py | 2
egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md | 2
funasr/tasks/diar.py | 70 ++--
funasr/tasks/abs_task.py | 8
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/README.md | 2
README.md | 30 -
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/infer.py | 13
egs/aishell/data2vec_paraformer_finetune/run.sh | 2
funasr/runtime/onnxruntime/src/librapidasrapi.cpp | 17
funasr/bin/asr_inference_uniasr.py | 2
egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py | 7
funasr/bin/asr_inference.py | 2
funasr/utils/timestamp_tools.py | 186 +++++++++++
egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md | 2
egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/README.md | 2
funasr/bin/eend_ola_inference.py | 26 +
egs/aishell2/paraformer/run.sh | 2
egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/README.md | 2
funasr/models/e2e_diar_eend_ola.py | 35 +
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer_after_finetune.py | 2
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/finetune.py | 35 ++
funasr/modules/eend_ola/encoder_decoder_attractor.py | 6
funasr/modules/eend_ola/encoder.py | 2
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py | 2
funasr/bin/asr_inference_rnnt.py | 2
egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py | 2
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline/infer_after_finetune.py | 2
funasr/runtime/onnxruntime/tester/tester.cpp | 57 +++
egs/aishell2/paraformerbert/run.sh | 2
egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer_after_finetune.py | 2
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/finetune.py | 35 ++
funasr/main_funcs/pack_funcs.py | 4
egs/alimeeting/diarization/sond/unit_test.py | 8
egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer_after_finetune.py | 2
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline/README.md | 2
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/infer_after_finetune.py | 2
egs/aishell2/transformerLM/run.sh | 2
funasr/tasks/sv.py | 2
egs/mars/sd/local_run.sh | 2
funasr/bin/diar_inference_launch.py | 5
funasr/runtime/python/README.md | 21 +
funasr/tasks/asr.py | 4
egs/aishell2/conformer/run.sh | 2
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/README.md | 2
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/finetune.py | 35 ++
egs/alimeeting/diarization/sond/run.sh | 6
funasr/models/frontend/wav_frontend.py | 77 ++++
egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/infer_after_finetune.py | 2
egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/infer_after_finetune.py | 2
egs/aishell2/transformer/run.sh | 2
funasr/main_funcs/average_nbest_models.py | 18
egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md | 2
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md | 3
egs/aishell/paraformer/run.sh | 2
funasr/bin/sv_inference.py | 4
egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer_after_finetune.py | 2
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer_after_finetune.py | 2
78 files changed, 684 insertions(+), 217 deletions(-)
diff --git a/README.md b/README.md
index 0d1079b..23f1abe 100644
--- a/README.md
+++ b/README.md
@@ -15,36 +15,10 @@
| [**Model Zoo**](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)
| [**Contact**](#contact)
+
## What's new:
-### 2023.2.17, funasr-0.2.0, modelscope-1.3.0
-- We support a new feature, export paraformer models into [onnx and torchscripts](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/export) from modelscope. The local finetuned models are also supported.
-- We support a new feature, [onnxruntime](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python), you could deploy the runtime without modelscope or funasr, for the [paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) model, the rtf of onnxruntime is 3x speedup(0.110->0.038) on cpu, [details](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python/onnxruntime/paraformer/rapid_paraformer#speed).
-- We support a new feature, [grpc](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python/grpc), you could build the ASR service with grpc, by deploying the modelscope pipeline or onnxruntime.
-- We release a new model [paraformer-large-contextual](https://www.modelscope.cn/models/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/summary), which supports the hotword customization based on the incentive enhancement, and improves the recall and precision of hotwords.
-- We optimize the timestamp alignment of [Paraformer-large-long](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary), the prediction accuracy of timestamp is much improved, and achieving accumulated average shift (aas) of 74.7ms, [details](https://arxiv.org/abs/2301.12343).
-- We release a new model, [8k VAD model](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary), which could predict the duration of none-silence speech. It could be freely integrated with any ASR models in [modelscope](https://github.com/alibaba-damo-academy/FunASR/discussions/134).
-- We release a new model, [MFCCA](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary), a multi-channel multi-speaker model which is independent of the number and geometry of microphones and supports Mandarin meeting transcription.
-- We release several new UniASR model:
-[Southern Fujian Dialect model](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/summary),
-[French model](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-fr-16k-common-vocab3472-tensorflow1-online/summary),
-[German model](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-de-16k-common-vocab3690-tensorflow1-online/summary),
-[Vietnamese model](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-online/summary),
-[Persian model](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/summary).
-- We release a new model, [paraformer-data2vec model](https://www.modelscope.cn/models/damo/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/summary), an unsupervised pretraining model on AISHELL-2, which is inited for paraformer model and then finetune on AISHEL-1.
-- We release a new feature, the `VAD`, `ASR` and `PUNC` models could be integrated freely, which could be models from [modelscope](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary), or the local finetine models. The [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/134).
-- We optimized the [punctuation common model](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/summary), enhance the recall and precision, fix the badcases of missing punctuation marks.
-- Various new types of audio input types are now supported by modelscope inference pipeline, including: mp3銆乫lac銆乷gg銆乷pus...
-### 2023.1.16, funasr-0.1.6锛� modelscope-1.2.0
-- We release a new version model [Paraformer-large-long](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary), which integrate the [VAD](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) model, [ASR](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary),
- [Punctuation](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/summary) model and timestamp together. The model could take in several hours long inputs.
-- We release a new model, [16k VAD model](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary), which could predict the duration of none-silence speech. It could be freely integrated with any ASR models in [modelscope](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary).
-- We release a new model, [Punctuation](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/summary), which could predict the punctuation of ASR models's results. It could be freely integrated with any ASR models in [Model Zoo](docs/modelscope_models.md).
-- We release a new model, [Data2vec](https://www.modelscope.cn/models/damo/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/summary), an unsupervised pretraining model which could be finetuned on ASR and other downstream tasks.
-- We release a new model, [Paraformer-Tiny](https://www.modelscope.cn/models/damo/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/summary), a lightweight Paraformer model which supports Mandarin command words recognition.
-- We release a new model, [SV](https://www.modelscope.cn/models/damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/summary), which could extract speaker embeddings and further perform speaker verification on paired utterances. It will be supported for speaker diarization in the future version.
-- We improve the pipeline of modelscope to speedup the inference, by integrating the process of build model into build pipeline.
-- Various new types of audio input types are now supported by modelscope inference pipeline, including wav.scp, wav format, audio bytes, wave samples...
+For the release notes, please ref to [news](https://github.com/alibaba-damo-academy/FunASR/releases)
## Highlights
- Many types of typical models are supported, e.g., [Tranformer](https://arxiv.org/abs/1706.03762), [Conformer](https://arxiv.org/abs/2005.08100), [Paraformer](https://arxiv.org/abs/2206.08317).
diff --git a/egs/aishell/conformer/run.sh b/egs/aishell/conformer/run.sh
index 41db45d..09ddab8 100755
--- a/egs/aishell/conformer/run.sh
+++ b/egs/aishell/conformer/run.sh
@@ -52,7 +52,7 @@
model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer.yaml
-inference_asr_model=valid.acc.ave_10best.pth
+inference_asr_model=valid.acc.ave_10best.pb
# you can set gpu num for decoding here
gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, the same as training stage by default
diff --git a/egs/aishell/data2vec_paraformer_finetune/run.sh b/egs/aishell/data2vec_paraformer_finetune/run.sh
index cada164..d033ce2 100755
--- a/egs/aishell/data2vec_paraformer_finetune/run.sh
+++ b/egs/aishell/data2vec_paraformer_finetune/run.sh
@@ -55,7 +55,7 @@
model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer_noctc_1best.yaml
-inference_asr_model=valid.acc.ave_10best.pth
+inference_asr_model=valid.acc.ave_10best.pb
# you can set gpu num for decoding here
gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, the same as training stage by default
diff --git a/egs/aishell/data2vec_transformer_finetune/run.sh b/egs/aishell/data2vec_transformer_finetune/run.sh
index 7ab8626..26222e6 100755
--- a/egs/aishell/data2vec_transformer_finetune/run.sh
+++ b/egs/aishell/data2vec_transformer_finetune/run.sh
@@ -55,7 +55,7 @@
model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer.yaml
-inference_asr_model=valid.cer_ctc.ave_10best.pth
+inference_asr_model=valid.cer_ctc.ave_10best.pb
# you can set gpu num for decoding here
gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, the same as training stage by default
diff --git a/egs/aishell/paraformer/run.sh b/egs/aishell/paraformer/run.sh
index 2b0f144..53b5f90 100755
--- a/egs/aishell/paraformer/run.sh
+++ b/egs/aishell/paraformer/run.sh
@@ -52,7 +52,7 @@
model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer_noctc_1best.yaml
-inference_asr_model=valid.acc.ave_10best.pth
+inference_asr_model=valid.acc.ave_10best.pb
# you can set gpu num for decoding here
gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, the same as training stage by default
diff --git a/egs/aishell/paraformerbert/run.sh b/egs/aishell/paraformerbert/run.sh
index 96310ab..2487eac 100755
--- a/egs/aishell/paraformerbert/run.sh
+++ b/egs/aishell/paraformerbert/run.sh
@@ -56,7 +56,7 @@
model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer_noctc_1best.yaml
-inference_asr_model=valid.acc.ave_10best.pth
+inference_asr_model=valid.acc.ave_10best.pb
# you can set gpu num for decoding here
gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, the same as training stage by default
diff --git a/egs/aishell/transformer/run.sh b/egs/aishell/transformer/run.sh
index 4c307b0..f66a338 100755
--- a/egs/aishell/transformer/run.sh
+++ b/egs/aishell/transformer/run.sh
@@ -52,7 +52,7 @@
model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer.yaml
-inference_asr_model=valid.acc.ave_10best.pth
+inference_asr_model=valid.acc.ave_10best.pb
# you can set gpu num for decoding here
gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, the same as training stage by default
diff --git a/egs/aishell2/conformer/run.sh b/egs/aishell2/conformer/run.sh
index bd6d81e..f9ea69a 100755
--- a/egs/aishell2/conformer/run.sh
+++ b/egs/aishell2/conformer/run.sh
@@ -54,7 +54,7 @@
model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer.yaml
-inference_asr_model=valid.acc.ave_10best.pth
+inference_asr_model=valid.acc.ave_10best.pb
# you can set gpu num for decoding here
gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, e.g., gpuid_list=2,3, the same as training stage by default
diff --git a/egs/aishell2/paraformer/run.sh b/egs/aishell2/paraformer/run.sh
index 2b7d841..e1ea4fe 100755
--- a/egs/aishell2/paraformer/run.sh
+++ b/egs/aishell2/paraformer/run.sh
@@ -54,7 +54,7 @@
model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer_noctc_1best.yaml
-inference_asr_model=valid.acc.ave_10best.pth
+inference_asr_model=valid.acc.ave_10best.pb
# you can set gpu num for decoding here
gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, e.g., gpuid_list=2,3, the same as training stage by default
diff --git a/egs/aishell2/paraformerbert/run.sh b/egs/aishell2/paraformerbert/run.sh
index d0407d4..239a7e3 100755
--- a/egs/aishell2/paraformerbert/run.sh
+++ b/egs/aishell2/paraformerbert/run.sh
@@ -58,7 +58,7 @@
model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer_noctc_1best.yaml
-inference_asr_model=valid.acc.ave_10best.pth
+inference_asr_model=valid.acc.ave_10best.pb
# you can set gpu num for decoding here
gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, e.g., gpuid_list=2,3, the same as training stage by default
diff --git a/egs/aishell2/transformer/run.sh b/egs/aishell2/transformer/run.sh
index a5a14ec..6f2dd4d 100755
--- a/egs/aishell2/transformer/run.sh
+++ b/egs/aishell2/transformer/run.sh
@@ -54,7 +54,7 @@
model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer.yaml
-inference_asr_model=valid.acc.ave_10best.pth
+inference_asr_model=valid.acc.ave_10best.pb
# you can set gpu num for decoding here
gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, e.g., gpuid_list=2,3, the same as training stage by default
diff --git a/egs/aishell2/transformerLM/run.sh b/egs/aishell2/transformerLM/run.sh
index 28e3762..9e7a713 100755
--- a/egs/aishell2/transformerLM/run.sh
+++ b/egs/aishell2/transformerLM/run.sh
@@ -34,7 +34,7 @@
tag=exp1
model_dir="baseline_$(basename "${lm_config}" .yaml)_${lang}_${token_type}_${tag}"
lm_exp=${exp_dir}/exp/${model_dir}
-inference_lm=valid.loss.ave.pth # Language model path for decoding.
+inference_lm=valid.loss.ave.pb # Language model path for decoding.
stage=0
stop_stage=3
diff --git a/egs/alimeeting/diarization/sond/infer_alimeeting_test.py b/egs/alimeeting/diarization/sond/infer_alimeeting_test.py
index 0988f5d..b4d534b 100644
--- a/egs/alimeeting/diarization/sond/infer_alimeeting_test.py
+++ b/egs/alimeeting/diarization/sond/infer_alimeeting_test.py
@@ -4,7 +4,7 @@
def main():
diar_config_path = sys.argv[1] if len(sys.argv) > 1 else "sond_fbank.yaml"
- diar_model_path = sys.argv[2] if len(sys.argv) > 2 else "sond.pth"
+ diar_model_path = sys.argv[2] if len(sys.argv) > 2 else "sond.pb"
output_dir = sys.argv[3] if len(sys.argv) > 3 else "./outputs"
data_path_and_name_and_type = [
("data/test_rmsil/feats.scp", "speech", "kaldi_ark"),
diff --git a/egs/alimeeting/diarization/sond/run.sh b/egs/alimeeting/diarization/sond/run.sh
index 7e9a7f7..19ae40c 100644
--- a/egs/alimeeting/diarization/sond/run.sh
+++ b/egs/alimeeting/diarization/sond/run.sh
@@ -17,9 +17,9 @@
echo "Downloading Pre-trained model..."
git clone https://www.modelscope.cn/damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch.git
git clone https://www.modelscope.cn/damo/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch.git
- ln -s speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/sv.pth ./sv.pth
+ ln -s speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/sv.pb ./sv.pb
cp speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/sv.yaml ./sv.yaml
- ln -s speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/sond.pth ./sond.pth
+ ln -s speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/sond.pb ./sond.pb
cp speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/sond_fbank.yaml ./sond_fbank.yaml
cp speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/sond.yaml ./sond.yaml
echo "Done."
@@ -30,7 +30,7 @@
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
echo "Calculating diarization results..."
- python infer_alimeeting_test.py sond_fbank.yaml sond.pth outputs
+ python infer_alimeeting_test.py sond_fbank.yaml sond.pb outputs
python local/convert_label_to_rttm.py \
outputs/labels.txt \
data/test_rmsil/raw_rmsil_map.scp \
diff --git a/egs/alimeeting/diarization/sond/unit_test.py b/egs/alimeeting/diarization/sond/unit_test.py
index 84a4247..0f40ab2 100644
--- a/egs/alimeeting/diarization/sond/unit_test.py
+++ b/egs/alimeeting/diarization/sond/unit_test.py
@@ -4,7 +4,7 @@
def test_fbank_cpu_infer():
diar_config_path = "config_fbank.yaml"
- diar_model_path = "sond.pth"
+ diar_model_path = "sond.pb"
output_dir = "./outputs"
data_path_and_name_and_type = [
("data/unit_test/test_feats.scp", "speech", "kaldi_ark"),
@@ -24,7 +24,7 @@
def test_fbank_gpu_infer():
diar_config_path = "config_fbank.yaml"
- diar_model_path = "sond.pth"
+ diar_model_path = "sond.pb"
output_dir = "./outputs"
data_path_and_name_and_type = [
("data/unit_test/test_feats.scp", "speech", "kaldi_ark"),
@@ -45,7 +45,7 @@
def test_wav_gpu_infer():
diar_config_path = "config.yaml"
- diar_model_path = "sond.pth"
+ diar_model_path = "sond.pb"
output_dir = "./outputs"
data_path_and_name_and_type = [
("data/unit_test/test_wav.scp", "speech", "sound"),
@@ -66,7 +66,7 @@
def test_without_profile_gpu_infer():
diar_config_path = "config.yaml"
- diar_model_path = "sond.pth"
+ diar_model_path = "sond.pb"
output_dir = "./outputs"
raw_inputs = [[
"data/unit_test/raw_inputs/record.wav",
diff --git a/egs/callhome/diarization/sond/unit_test.py b/egs/callhome/diarization/sond/unit_test.py
index 519ac56..a48eda1 100644
--- a/egs/callhome/diarization/sond/unit_test.py
+++ b/egs/callhome/diarization/sond/unit_test.py
@@ -4,7 +4,7 @@
def test_fbank_cpu_infer():
diar_config_path = "sond_fbank.yaml"
- diar_model_path = "sond.pth"
+ diar_model_path = "sond.pb"
output_dir = "./outputs"
data_path_and_name_and_type = [
("data/unit_test/test_feats.scp", "speech", "kaldi_ark"),
@@ -24,7 +24,7 @@
def test_fbank_gpu_infer():
diar_config_path = "sond_fbank.yaml"
- diar_model_path = "sond.pth"
+ diar_model_path = "sond.pb"
output_dir = "./outputs"
data_path_and_name_and_type = [
("data/unit_test/test_feats.scp", "speech", "kaldi_ark"),
@@ -45,7 +45,7 @@
def test_wav_gpu_infer():
diar_config_path = "config.yaml"
- diar_model_path = "sond.pth"
+ diar_model_path = "sond.pb"
output_dir = "./outputs"
data_path_and_name_and_type = [
("data/unit_test/test_wav.scp", "speech", "sound"),
@@ -66,7 +66,7 @@
def test_without_profile_gpu_infer():
diar_config_path = "config.yaml"
- diar_model_path = "sond.pth"
+ diar_model_path = "sond.pb"
output_dir = "./outputs"
raw_inputs = [[
"data/unit_test/raw_inputs/record.wav",
diff --git a/egs/mars/sd/local_run.sh b/egs/mars/sd/local_run.sh
index 3b319f4..4516e9f 100755
--- a/egs/mars/sd/local_run.sh
+++ b/egs/mars/sd/local_run.sh
@@ -49,7 +49,7 @@
model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer.yaml
-inference_asr_model=valid.acc.ave_10best.pth
+inference_asr_model=valid.acc.ave_10best.pb
# you can set gpu num for decoding here
gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, the same as training stage by default
diff --git a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/README.md b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/README.md
index c2e4354..053986d 100644
--- a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/README.md
+++ b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/README.md
@@ -41,7 +41,7 @@
- Modify inference related parameters in `infer_after_finetune.py`
- <strong>output_dir:</strong> # result dir
- <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed~~~~
- - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pth`
+ - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb`
- Then you can run the pipeline to finetune with:
```python
diff --git a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer_after_finetune.py b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer_after_finetune.py
index 56c282c..b326067 100644
--- a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer_after_finetune.py
+++ b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer_after_finetune.py
@@ -48,5 +48,5 @@
params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./data/test"
- params["decoding_model_name"] = "valid.cer_ctc.ave.pth"
+ params["decoding_model_name"] = "valid.cer_ctc.ave.pb"
modelscope_infer_after_finetune(params)
diff --git a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/README.md b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/README.md
index c2e4354..053986d 100644
--- a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/README.md
+++ b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/README.md
@@ -41,7 +41,7 @@
- Modify inference related parameters in `infer_after_finetune.py`
- <strong>output_dir:</strong> # result dir
- <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed~~~~
- - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pth`
+ - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb`
- Then you can run the pipeline to finetune with:
```python
diff --git a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer_after_finetune.py b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer_after_finetune.py
index e163999..2f038a8 100644
--- a/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer_after_finetune.py
+++ b/egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer_after_finetune.py
@@ -48,5 +48,5 @@
params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./data/test"
- params["decoding_model_name"] = "valid.cer_ctc.ave.pth"
+ params["decoding_model_name"] = "valid.cer_ctc.ave.pb"
modelscope_infer_after_finetune(params)
diff --git a/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md b/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md
index 9097e7a..16aeada 100644
--- a/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md
+++ b/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md
@@ -41,7 +41,7 @@
- Modify inference related parameters in `infer_after_finetune.py`
- <strong>output_dir:</strong> # result dir
- <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
- - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pth`
+ - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb`
- Then you can run the pipeline to finetune with:
```python
diff --git a/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer_after_finetune.py b/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer_after_finetune.py
index e714a3d..333b66a 100755
--- a/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer_after_finetune.py
+++ b/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer_after_finetune.py
@@ -63,5 +63,5 @@
params["required_files"] = ["feats_stats.npz", "decoding.yaml", "configuration.json"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./example_data/validation"
- params["decoding_model_name"] = "valid.acc.ave.pth"
+ params["decoding_model_name"] = "valid.acc.ave.pb"
modelscope_infer_after_finetune(params)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/infer_after_finetune.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/infer_after_finetune.py
index 6c34ed0..f1f29fa 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/infer_after_finetune.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/infer_after_finetune.py
@@ -49,5 +49,5 @@
params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./data/test"
- params["decoding_model_name"] = "valid.acc.ave_10best.pth"
+ params["decoding_model_name"] = "valid.acc.ave_10best.pb"
modelscope_infer_after_finetune(params)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/infer_after_finetune.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/infer_after_finetune.py
index 6140bb7..8cb537b 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/infer_after_finetune.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/infer_after_finetune.py
@@ -49,5 +49,5 @@
params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./data/test"
- params["decoding_model_name"] = "valid.acc.ave_10best.pth"
+ params["decoding_model_name"] = "valid.acc.ave_10best.pb"
modelscope_infer_after_finetune(params)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md
index dfd509d..b68f1e9 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md
@@ -41,7 +41,7 @@
- Modify inference related parameters in `infer_after_finetune.py`
- <strong>output_dir:</strong> # result dir
- <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
- - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pth`
+ - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb`
- Then you can run the pipeline to finetune with:
```python
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py
index 94393ec..f26f237 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py
@@ -49,5 +49,5 @@
params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./data/test"
- params["decoding_model_name"] = "valid.acc.ave_10best.pth"
+ params["decoding_model_name"] = "valid.acc.ave_10best.pb"
modelscope_infer_after_finetune(params)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py
index 96102cc..726009d 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py
@@ -49,5 +49,5 @@
params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./data/test"
- params["decoding_model_name"] = "valid.acc.ave_10best.pth"
+ params["decoding_model_name"] = "valid.acc.ave_10best.pb"
modelscope_infer_after_finetune(params)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline/README.md b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline/README.md
index dfd509d..b68f1e9 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline/README.md
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline/README.md
@@ -41,7 +41,7 @@
- Modify inference related parameters in `infer_after_finetune.py`
- <strong>output_dir:</strong> # result dir
- <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
- - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pth`
+ - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb`
- Then you can run the pipeline to finetune with:
```python
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline/infer_after_finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline/infer_after_finetune.py
index d91a40a..6593f4e 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline/infer_after_finetune.py
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline/infer_after_finetune.py
@@ -50,5 +50,5 @@
params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./data/test"
- params["decoding_model_name"] = "20epoch.pth"
+ params["decoding_model_name"] = "20epoch.pb"
modelscope_infer_after_finetune(params)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/README.md b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/README.md
index dfd509d..b68f1e9 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/README.md
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/README.md
@@ -41,7 +41,7 @@
- Modify inference related parameters in `infer_after_finetune.py`
- <strong>output_dir:</strong> # result dir
- <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
- - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pth`
+ - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb`
- Then you can run the pipeline to finetune with:
```python
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/infer_after_finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/infer_after_finetune.py
index f9fb0db..f067c81 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/infer_after_finetune.py
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/infer_after_finetune.py
@@ -50,5 +50,5 @@
params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./data/test"
- params["decoding_model_name"] = "20epoch.pth"
+ params["decoding_model_name"] = "20epoch.pb"
modelscope_infer_after_finetune(params)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/finetune.py
new file mode 100644
index 0000000..56fb583
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/finetune.py
@@ -0,0 +1,35 @@
+import os
+from modelscope.metainfo import Trainers
+from modelscope.trainers import build_trainer
+from funasr.datasets.ms_dataset import MsDataset
+
+
+def modelscope_finetune(params):
+ if not os.path.exists(params["output_dir"]):
+ os.makedirs(params["output_dir"], exist_ok=True)
+ # dataset split ["train", "validation"]
+ ds_dict = MsDataset.load(params["data_dir"])
+ kwargs = dict(
+ model=params["model"],
+ model_revision=params["model_revision"],
+ data_dir=ds_dict,
+ dataset_type=params["dataset_type"],
+ work_dir=params["output_dir"],
+ batch_bins=params["batch_bins"],
+ max_epoch=params["max_epoch"],
+ lr=params["lr"])
+ trainer = build_trainer(Trainers.speech_asr_trainer, default_args=kwargs)
+ trainer.train()
+
+
+if __name__ == '__main__':
+ params = {}
+ params["output_dir"] = "./checkpoint"
+ params["data_dir"] = "./data"
+ params["batch_bins"] = 2000
+ params["dataset_type"] = "small"
+ params["max_epoch"] = 50
+ params["lr"] = 0.00005
+ params["model"] = "damo/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch"
+ params["model_revision"] = None
+ modelscope_finetune(params)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/infer.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/infer.py
new file mode 100644
index 0000000..c54ab8c
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/infer.py
@@ -0,0 +1,13 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+if __name__ == "__main__":
+ audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_he.wav"
+ output_dir = "./results"
+ inference_pipline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model="damo/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch",
+ output_dir=output_dir,
+ )
+ rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+ print(rec_result)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/README.md b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/README.md
index dd947d3..9a84f9b 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/README.md
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/README.md
@@ -41,7 +41,7 @@
- Modify inference related parameters in `infer_after_finetune.py`
- <strong>output_dir:</strong> # result dir
- <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
- - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pth`
+ - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb`
- Then you can run the pipeline to finetune with:
```python
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer_after_finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer_after_finetune.py
index 030c2e2..d4df29e 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer_after_finetune.py
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer_after_finetune.py
@@ -50,5 +50,5 @@
params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./data/test"
- params["decoding_model_name"] = "20epoch.pth"
+ params["decoding_model_name"] = "20epoch.pb"
modelscope_infer_after_finetune(params)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/finetune.py
new file mode 100644
index 0000000..8bbce60
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/finetune.py
@@ -0,0 +1,35 @@
+import os
+from modelscope.metainfo import Trainers
+from modelscope.trainers import build_trainer
+from funasr.datasets.ms_dataset import MsDataset
+
+
+def modelscope_finetune(params):
+ if not os.path.exists(params["output_dir"]):
+ os.makedirs(params["output_dir"], exist_ok=True)
+ # dataset split ["train", "validation"]
+ ds_dict = MsDataset.load(params["data_dir"])
+ kwargs = dict(
+ model=params["model"],
+ model_revision=params["model_revision"],
+ data_dir=ds_dict,
+ dataset_type=params["dataset_type"],
+ work_dir=params["output_dir"],
+ batch_bins=params["batch_bins"],
+ max_epoch=params["max_epoch"],
+ lr=params["lr"])
+ trainer = build_trainer(Trainers.speech_asr_trainer, default_args=kwargs)
+ trainer.train()
+
+
+if __name__ == '__main__':
+ params = {}
+ params["output_dir"] = "./checkpoint"
+ params["data_dir"] = "./data"
+ params["batch_bins"] = 2000
+ params["dataset_type"] = "small"
+ params["max_epoch"] = 50
+ params["lr"] = 0.00005
+ params["model"] = "damo/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch"
+ params["model_revision"] = None
+ modelscope_finetune(params)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/infer.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/infer.py
new file mode 100644
index 0000000..cfd869f
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/infer.py
@@ -0,0 +1,13 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+if __name__ == "__main__":
+ audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_my.wav"
+ output_dir = "./results"
+ inference_pipline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model="damo/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch",
+ output_dir=output_dir,
+ )
+ rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+ print(rec_result)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/finetune.py
new file mode 100644
index 0000000..5e313e5
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/finetune.py
@@ -0,0 +1,35 @@
+import os
+from modelscope.metainfo import Trainers
+from modelscope.trainers import build_trainer
+from funasr.datasets.ms_dataset import MsDataset
+
+
+def modelscope_finetune(params):
+ if not os.path.exists(params["output_dir"]):
+ os.makedirs(params["output_dir"], exist_ok=True)
+ # dataset split ["train", "validation"]
+ ds_dict = MsDataset.load(params["data_dir"])
+ kwargs = dict(
+ model=params["model"],
+ model_revision=params["model_revision"],
+ data_dir=ds_dict,
+ dataset_type=params["dataset_type"],
+ work_dir=params["output_dir"],
+ batch_bins=params["batch_bins"],
+ max_epoch=params["max_epoch"],
+ lr=params["lr"])
+ trainer = build_trainer(Trainers.speech_asr_trainer, default_args=kwargs)
+ trainer.train()
+
+
+if __name__ == '__main__':
+ params = {}
+ params["output_dir"] = "./checkpoint"
+ params["data_dir"] = "./data"
+ params["batch_bins"] = 2000
+ params["dataset_type"] = "small"
+ params["max_epoch"] = 50
+ params["lr"] = 0.00005
+ params["model"] = "damo/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch"
+ params["model_revision"] = None
+ modelscope_finetune(params)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/infer.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/infer.py
new file mode 100644
index 0000000..e8c5524
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/infer.py
@@ -0,0 +1,13 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+if __name__ == "__main__":
+ audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ur.wav"
+ output_dir = "./results"
+ inference_pipline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model="damo/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch",
+ output_dir=output_dir,
+ )
+ rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+ print(rec_result)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/README.md b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/README.md
index dd947d3..9a84f9b 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/README.md
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/README.md
@@ -41,7 +41,7 @@
- Modify inference related parameters in `infer_after_finetune.py`
- <strong>output_dir:</strong> # result dir
- <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
- - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pth`
+ - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb`
- Then you can run the pipeline to finetune with:
```python
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py
index 3b39a16..861fefb 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py
@@ -49,5 +49,5 @@
params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./data/test"
- params["decoding_model_name"] = "20epoch.pth"
+ params["decoding_model_name"] = "20epoch.pb"
modelscope_infer_after_finetune(params)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md
index dd947d3..eff933e 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md
@@ -41,7 +41,8 @@
- Modify inference related parameters in `infer_after_finetune.py`
- <strong>output_dir:</strong> # result dir
- <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
- - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pth`
+ - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave
+ .pb`
- Then you can run the pipeline to finetune with:
```python
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer_after_finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer_after_finetune.py
index 4860cf7..d73cae2 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer_after_finetune.py
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer_after_finetune.py
@@ -49,5 +49,5 @@
params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./data/test"
- params["decoding_model_name"] = "20epoch.pth"
+ params["decoding_model_name"] = "20epoch.pb"
modelscope_infer_after_finetune(params)
diff --git a/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md b/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md
index 1094bb5..94144ef 100644
--- a/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md
+++ b/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md
@@ -34,7 +34,7 @@
- Modify inference related parameters in `infer_after_finetune.py`
- <strong>output_dir:</strong> # result dir
- <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
- - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pth`
+ - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb`
- Then you can run the pipeline to finetune with:
```python
diff --git a/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py b/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py
index 5f171b4..3712cb8 100644
--- a/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py
+++ b/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py
@@ -53,5 +53,5 @@
params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json", "punc/punc.pb", "punc/punc.yaml", "vad/vad.mvn", "vad/vad.pb", "vad/vad.yaml"]
params["output_dir"] = "./checkpoint"
params["data_dir"] = "./data/test"
- params["decoding_model_name"] = "valid.acc.ave_10best.pth"
+ params["decoding_model_name"] = "valid.acc.ave_10best.pb"
modelscope_infer_after_finetune(params)
diff --git a/egs_modelscope/speaker_diarization/speech_diarization_eend-ola-en-us-callhome-8k/infer.py b/egs_modelscope/speaker_diarization/speech_diarization_eend-ola-en-us-callhome-8k/infer.py
new file mode 100644
index 0000000..81cb2c6
--- /dev/null
+++ b/egs_modelscope/speaker_diarization/speech_diarization_eend-ola-en-us-callhome-8k/infer.py
@@ -0,0 +1,10 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_diar_pipline = pipeline(
+ task=Tasks.speaker_diarization,
+ model='damo/speech_diarization_eend-ola-en-us-callhome-8k',
+ model_revision="v1.0.0",
+)
+results = inference_diar_pipline(audio_in=["https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/record2.wav"])
+print(results)
\ No newline at end of file
diff --git a/egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py b/egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py
index 3cb31cf..5f4563d 100644
--- a/egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py
+++ b/egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py
@@ -14,13 +14,12 @@
)
# 浠� audio_list 浣滀负杈撳叆锛屽叾涓涓�涓煶棰戜负寰呮娴嬭闊筹紝鍚庨潰鐨勯煶棰戜负涓嶅悓璇磋瘽浜虹殑澹扮汗娉ㄥ唽璇煶
-audio_list = [[
+audio_list = [
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/record.wav",
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_A.wav",
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_B.wav",
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_B1.wav"
-]]
+]
results = inference_diar_pipline(audio_in=audio_list)
-for rst in results:
- print(rst["value"])
+print(results)
diff --git a/funasr/bin/asr_inference.py b/funasr/bin/asr_inference.py
index 318d3d7..f3b4d56 100644
--- a/funasr/bin/asr_inference.py
+++ b/funasr/bin/asr_inference.py
@@ -52,7 +52,7 @@
Examples:
>>> import soundfile
- >>> speech2text = Speech2Text("asr_config.yml", "asr.pth")
+ >>> speech2text = Speech2Text("asr_config.yml", "asr.pb")
>>> audio, rate = soundfile.read("speech.wav")
>>> speech2text(audio)
[(text, token, token_int, hypothesis object), ...]
diff --git a/funasr/bin/asr_inference_mfcca.py b/funasr/bin/asr_inference_mfcca.py
index 4176ba6..888d4d2 100644
--- a/funasr/bin/asr_inference_mfcca.py
+++ b/funasr/bin/asr_inference_mfcca.py
@@ -55,7 +55,7 @@
Examples:
>>> import soundfile
- >>> speech2text = Speech2Text("asr_config.yml", "asr.pth")
+ >>> speech2text = Speech2Text("asr_config.yml", "asr.pb")
>>> audio, rate = soundfile.read("speech.wav")
>>> speech2text(audio)
[(text, token, token_int, hypothesis object), ...]
diff --git a/funasr/bin/asr_inference_paraformer.py b/funasr/bin/asr_inference_paraformer.py
index 6413d92..e45e575 100644
--- a/funasr/bin/asr_inference_paraformer.py
+++ b/funasr/bin/asr_inference_paraformer.py
@@ -50,7 +50,7 @@
Examples:
>>> import soundfile
- >>> speech2text = Speech2Text("asr_config.yml", "asr.pth")
+ >>> speech2text = Speech2Text("asr_config.yml", "asr.pb")
>>> audio, rate = soundfile.read("speech.wav")
>>> speech2text(audio)
[(text, token, token_int, hypothesis object), ...]
diff --git a/funasr/bin/asr_inference_paraformer_vad_punc.py b/funasr/bin/asr_inference_paraformer_vad_punc.py
index a0e7b47..3f57751 100644
--- a/funasr/bin/asr_inference_paraformer_vad_punc.py
+++ b/funasr/bin/asr_inference_paraformer_vad_punc.py
@@ -58,7 +58,7 @@
Examples:
>>> import soundfile
- >>> speech2text = Speech2Text("asr_config.yml", "asr.pth")
+ >>> speech2text = Speech2Text("asr_config.yml", "asr.pb")
>>> audio, rate = soundfile.read("speech.wav")
>>> speech2text(audio)
[(text, token, token_int, hypothesis object), ...]
diff --git a/funasr/bin/asr_inference_rnnt.py b/funasr/bin/asr_inference_rnnt.py
index 6cd7061..4a9ff0b 100644
--- a/funasr/bin/asr_inference_rnnt.py
+++ b/funasr/bin/asr_inference_rnnt.py
@@ -49,7 +49,7 @@
Examples:
>>> import soundfile
- >>> speech2text = Speech2Text("asr_config.yml", "asr.pth")
+ >>> speech2text = Speech2Text("asr_config.yml", "asr.pb")
>>> audio, rate = soundfile.read("speech.wav")
>>> speech2text(audio)
[(text, token, token_int, hypothesis object), ...]
diff --git a/funasr/bin/asr_inference_uniasr.py b/funasr/bin/asr_inference_uniasr.py
index 8b31fad..ac71538 100644
--- a/funasr/bin/asr_inference_uniasr.py
+++ b/funasr/bin/asr_inference_uniasr.py
@@ -46,7 +46,7 @@
Examples:
>>> import soundfile
- >>> speech2text = Speech2Text("asr_config.yml", "asr.pth")
+ >>> speech2text = Speech2Text("asr_config.yml", "asr.pb")
>>> audio, rate = soundfile.read("speech.wav")
>>> speech2text(audio)
[(text, token, token_int, hypothesis object), ...]
diff --git a/funasr/bin/asr_inference_uniasr_vad.py b/funasr/bin/asr_inference_uniasr_vad.py
index e5815df..7cb889b 100644
--- a/funasr/bin/asr_inference_uniasr_vad.py
+++ b/funasr/bin/asr_inference_uniasr_vad.py
@@ -46,7 +46,7 @@
Examples:
>>> import soundfile
- >>> speech2text = Speech2Text("asr_config.yml", "asr.pth")
+ >>> speech2text = Speech2Text("asr_config.yml", "asr.pb")
>>> audio, rate = soundfile.read("speech.wav")
>>> speech2text(audio)
[(text, token, token_int, hypothesis object), ...]
diff --git a/funasr/bin/diar_inference_launch.py b/funasr/bin/diar_inference_launch.py
index 7738f4f..85e4518 100755
--- a/funasr/bin/diar_inference_launch.py
+++ b/funasr/bin/diar_inference_launch.py
@@ -133,7 +133,7 @@
param_dict = {
"extract_profile": True,
"sv_train_config": "sv.yaml",
- "sv_model_file": "sv.pth",
+ "sv_model_file": "sv.pb",
}
if "param_dict" in kwargs and kwargs["param_dict"] is not None:
for key in param_dict:
@@ -142,6 +142,9 @@
else:
kwargs["param_dict"] = param_dict
return inference_modelscope(mode=mode, **kwargs)
+ elif mode == "eend-ola":
+ from funasr.bin.eend_ola_inference import inference_modelscope
+ return inference_modelscope(mode=mode, **kwargs)
else:
logging.info("Unknown decoding mode: {}".format(mode))
return None
diff --git a/funasr/bin/eend_ola_inference.py b/funasr/bin/eend_ola_inference.py
index d65895f..01d3f29 100755
--- a/funasr/bin/eend_ola_inference.py
+++ b/funasr/bin/eend_ola_inference.py
@@ -16,6 +16,7 @@
import numpy as np
import torch
+from scipy.signal import medfilt
from typeguard import check_argument_types
from funasr.models.frontend.wav_frontend import WavFrontendMel23
@@ -34,7 +35,7 @@
Examples:
>>> import soundfile
>>> import numpy as np
- >>> speech2diar = Speech2Diarization("diar_sond_config.yml", "diar_sond.pth")
+ >>> speech2diar = Speech2Diarization("diar_sond_config.yml", "diar_sond.pb")
>>> profile = np.load("profiles.npy")
>>> audio, rate = soundfile.read("speech.wav")
>>> speech2diar(audio, profile)
@@ -146,7 +147,7 @@
output_dir: Optional[str] = None,
batch_size: int = 1,
dtype: str = "float32",
- ngpu: int = 0,
+ ngpu: int = 1,
num_workers: int = 0,
log_level: Union[int, str] = "INFO",
key_file: Optional[str] = None,
@@ -179,7 +180,6 @@
diar_model_file=diar_model_file,
device=device,
dtype=dtype,
- streaming=streaming,
)
logging.info("speech2diarization_kwargs: {}".format(speech2diar_kwargs))
speech2diar = Speech2Diarization.from_pretrained(
@@ -209,7 +209,7 @@
if data_path_and_name_and_type is None and raw_inputs is not None:
if isinstance(raw_inputs, torch.Tensor):
raw_inputs = raw_inputs.numpy()
- data_path_and_name_and_type = [raw_inputs, "speech", "waveform"]
+ data_path_and_name_and_type = [raw_inputs[0], "speech", "sound"]
loader = EENDOLADiarTask.build_streaming_iterator(
data_path_and_name_and_type,
dtype=dtype,
@@ -236,9 +236,23 @@
# batch = {k: v[0] for k, v in batch.items() if not k.endswith("_lengths")}
results = speech2diar(**batch)
+
+ # post process
+ a = results[0][0].cpu().numpy()
+ a = medfilt(a, (11, 1))
+ rst = []
+ for spkid, frames in enumerate(a.T):
+ frames = np.pad(frames, (1, 1), 'constant')
+ changes, = np.where(np.diff(frames, axis=0) != 0)
+ fmt = "SPEAKER {:s} 1 {:7.2f} {:7.2f} <NA> <NA> {:s} <NA>"
+ for s, e in zip(changes[::2], changes[1::2]):
+ st = s / 10.
+ dur = (e - s) / 10.
+ rst.append(fmt.format(keys[0], st, dur, "{}_{}".format(keys[0], str(spkid))))
+
# Only supporting batch_size==1
- key, value = keys[0], output_results_str(results, keys[0])
- item = {"key": key, "value": value}
+ value = "\n".join(rst)
+ item = {"key": keys[0], "value": value}
result_list.append(item)
if output_path is not None:
output_writer.write(value)
diff --git a/funasr/bin/sond_inference.py b/funasr/bin/sond_inference.py
index ab6d26f..936dc21 100755
--- a/funasr/bin/sond_inference.py
+++ b/funasr/bin/sond_inference.py
@@ -42,7 +42,7 @@
Examples:
>>> import soundfile
>>> import numpy as np
- >>> speech2diar = Speech2Diarization("diar_sond_config.yml", "diar_sond.pth")
+ >>> speech2diar = Speech2Diarization("diar_sond_config.yml", "diar_sond.pb")
>>> profile = np.load("profiles.npy")
>>> audio, rate = soundfile.read("speech.wav")
>>> speech2diar(audio, profile)
diff --git a/funasr/bin/sv_inference.py b/funasr/bin/sv_inference.py
index a78bccd..7e63bbd 100755
--- a/funasr/bin/sv_inference.py
+++ b/funasr/bin/sv_inference.py
@@ -36,7 +36,7 @@
Examples:
>>> import soundfile
- >>> speech2xvector = Speech2Xvector("sv_config.yml", "sv.pth")
+ >>> speech2xvector = Speech2Xvector("sv_config.yml", "sv.pb")
>>> audio, rate = soundfile.read("speech.wav")
>>> speech2xvector(audio)
[(text, token, token_int, hypothesis object), ...]
@@ -169,7 +169,7 @@
log_level: Union[int, str] = "INFO",
key_file: Optional[str] = None,
sv_train_config: Optional[str] = "sv.yaml",
- sv_model_file: Optional[str] = "sv.pth",
+ sv_model_file: Optional[str] = "sv.pb",
model_tag: Optional[str] = None,
allow_variable_data_keys: bool = True,
streaming: bool = False,
diff --git a/funasr/main_funcs/average_nbest_models.py b/funasr/main_funcs/average_nbest_models.py
index 53f9568..d8df949 100644
--- a/funasr/main_funcs/average_nbest_models.py
+++ b/funasr/main_funcs/average_nbest_models.py
@@ -66,13 +66,13 @@
elif n == 1:
# The averaged model is same as the best model
e, _ = epoch_and_values[0]
- op = output_dir / f"{e}epoch.pth"
- sym_op = output_dir / f"{ph}.{cr}.ave_1best.{suffix}pth"
+ op = output_dir / f"{e}epoch.pb"
+ sym_op = output_dir / f"{ph}.{cr}.ave_1best.{suffix}pb"
if sym_op.is_symlink() or sym_op.exists():
sym_op.unlink()
sym_op.symlink_to(op.name)
else:
- op = output_dir / f"{ph}.{cr}.ave_{n}best.{suffix}pth"
+ op = output_dir / f"{ph}.{cr}.ave_{n}best.{suffix}pb"
logging.info(
f"Averaging {n}best models: " f'criterion="{ph}.{cr}": {op}'
)
@@ -83,12 +83,12 @@
if e not in _loaded:
if oss_bucket is None:
_loaded[e] = torch.load(
- output_dir / f"{e}epoch.pth",
+ output_dir / f"{e}epoch.pb",
map_location="cpu",
)
else:
buffer = BytesIO(
- oss_bucket.get_object(os.path.join(pai_output_dir, f"{e}epoch.pth")).read())
+ oss_bucket.get_object(os.path.join(pai_output_dir, f"{e}epoch.pb")).read())
_loaded[e] = torch.load(buffer)
states = _loaded[e]
@@ -115,13 +115,13 @@
else:
buffer = BytesIO()
torch.save(avg, buffer)
- oss_bucket.put_object(os.path.join(pai_output_dir, f"{ph}.{cr}.ave_{n}best.{suffix}pth"),
+ oss_bucket.put_object(os.path.join(pai_output_dir, f"{ph}.{cr}.ave_{n}best.{suffix}pb"),
buffer.getvalue())
- # 3. *.*.ave.pth is a symlink to the max ave model
+ # 3. *.*.ave.pb is a symlink to the max ave model
if oss_bucket is None:
- op = output_dir / f"{ph}.{cr}.ave_{max(_nbests)}best.{suffix}pth"
- sym_op = output_dir / f"{ph}.{cr}.ave.{suffix}pth"
+ op = output_dir / f"{ph}.{cr}.ave_{max(_nbests)}best.{suffix}pb"
+ sym_op = output_dir / f"{ph}.{cr}.ave.{suffix}pb"
if sym_op.is_symlink() or sym_op.exists():
sym_op.unlink()
sym_op.symlink_to(op.name)
diff --git a/funasr/main_funcs/pack_funcs.py b/funasr/main_funcs/pack_funcs.py
index ffa807e..fe365d8 100644
--- a/funasr/main_funcs/pack_funcs.py
+++ b/funasr/main_funcs/pack_funcs.py
@@ -191,12 +191,12 @@
Examples:
tarfile:
- model.pth
+ model.pb
some1.file
some2.file
>>> unpack("tarfile", "out")
- {'asr_model_file': 'out/model.pth'}
+ {'asr_model_file': 'out/model.pb'}
"""
input_archive = Path(input_archive)
outpath = Path(outpath)
diff --git a/funasr/models/e2e_diar_eend_ola.py b/funasr/models/e2e_diar_eend_ola.py
index f589269..097b23a 100644
--- a/funasr/models/e2e_diar_eend_ola.py
+++ b/funasr/models/e2e_diar_eend_ola.py
@@ -52,15 +52,15 @@
super().__init__()
self.frontend = frontend
- self.encoder = encoder
- self.encoder_decoder_attractor = encoder_decoder_attractor
+ self.enc = encoder
+ self.eda = encoder_decoder_attractor
self.attractor_loss_weight = attractor_loss_weight
self.max_n_speaker = max_n_speaker
if mapping_dict is None:
mapping_dict = generate_mapping_dict(max_speaker_num=self.max_n_speaker)
self.mapping_dict = mapping_dict
# PostNet
- self.PostNet = nn.LSTM(self.max_n_speaker, n_units, 1, batch_first=True)
+ self.postnet = nn.LSTM(self.max_n_speaker, n_units, 1, batch_first=True)
self.output_layer = nn.Linear(n_units, mapping_dict['oov'] + 1)
def forward_encoder(self, xs, ilens):
@@ -68,7 +68,7 @@
pad_shape = xs.shape
xs_mask = [torch.ones(ilen).to(xs.device) for ilen in ilens]
xs_mask = torch.nn.utils.rnn.pad_sequence(xs_mask, batch_first=True, padding_value=0).unsqueeze(-2)
- emb = self.encoder(xs, xs_mask)
+ emb = self.enc(xs, xs_mask)
emb = torch.split(emb.view(pad_shape[0], pad_shape[1], -1), 1, dim=0)
emb = [e[0][:ilen] for e, ilen in zip(emb, ilens)]
return emb
@@ -76,8 +76,8 @@
def forward_post_net(self, logits, ilens):
maxlen = torch.max(ilens).to(torch.int).item()
logits = nn.utils.rnn.pad_sequence(logits, batch_first=True, padding_value=-1)
- logits = nn.utils.rnn.pack_padded_sequence(logits, ilens, batch_first=True, enforce_sorted=False)
- outputs, (_, _) = self.PostNet(logits)
+ logits = nn.utils.rnn.pack_padded_sequence(logits, ilens.cpu().to(torch.int64), batch_first=True, enforce_sorted=False)
+ outputs, (_, _) = self.postnet(logits)
outputs = nn.utils.rnn.pad_packed_sequence(outputs, batch_first=True, padding_value=-1, total_length=maxlen)[0]
outputs = [output[:ilens[i].to(torch.int).item()] for i, output in enumerate(outputs)]
outputs = [self.output_layer(output) for output in outputs]
@@ -112,7 +112,7 @@
text = text[:, : text_lengths.max()]
# 1. Encoder
- encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
+ encoder_out, encoder_out_lens = self.enc(speech, speech_lengths)
intermediate_outs = None
if isinstance(encoder_out, tuple):
intermediate_outs = encoder_out[1]
@@ -190,18 +190,16 @@
shuffle: bool = True,
threshold: float = 0.5,
**kwargs):
- if self.frontend is not None:
- speech = self.frontend(speech)
speech = [s[:s_len] for s, s_len in zip(speech, speech_lengths)]
emb = self.forward_encoder(speech, speech_lengths)
if shuffle:
orders = [np.arange(e.shape[0]) for e in emb]
for order in orders:
np.random.shuffle(order)
- attractors, probs = self.encoder_decoder_attractor.estimate(
+ attractors, probs = self.eda.estimate(
[e[torch.from_numpy(order).to(torch.long).to(speech[0].device)] for e, order in zip(emb, orders)])
else:
- attractors, probs = self.encoder_decoder_attractor.estimate(emb)
+ attractors, probs = self.eda.estimate(emb)
attractors_active = []
for p, att, e in zip(probs, attractors, emb):
if n_speakers and n_speakers >= 0:
@@ -233,10 +231,23 @@
pred[i] = pred[i - 1]
else:
pred[i] = 0
- pred = [self.reporter.inv_mapping_func(i, self.mapping_dict) for i in pred]
+ pred = [self.inv_mapping_func(i) for i in pred]
decisions = [bin(num)[2:].zfill(self.max_n_speaker)[::-1] for num in pred]
decisions = torch.from_numpy(
np.stack([np.array([int(i) for i in dec]) for dec in decisions], axis=0)).to(logit.device).to(
torch.float32)
decisions = decisions[:, :n_speaker]
return decisions
+
+ def inv_mapping_func(self, label):
+
+ if not isinstance(label, int):
+ label = int(label)
+ if label in self.mapping_dict['label2dec'].keys():
+ num = self.mapping_dict['label2dec'][label]
+ else:
+ num = -1
+ return num
+
+ def collect_feats(self, **batch: torch.Tensor) -> Dict[str, torch.Tensor]:
+ pass
\ No newline at end of file
diff --git a/funasr/models/frontend/wav_frontend.py b/funasr/models/frontend/wav_frontend.py
index 445efca..475a939 100644
--- a/funasr/models/frontend/wav_frontend.py
+++ b/funasr/models/frontend/wav_frontend.py
@@ -1,14 +1,15 @@
# Copyright (c) Alibaba, Inc. and its affiliates.
# Part of the implementation is borrowed from espnet/espnet.
-from abc import ABC
from typing import Tuple
import numpy as np
import torch
import torchaudio.compliance.kaldi as kaldi
-from funasr.models.frontend.abs_frontend import AbsFrontend
-from typeguard import check_argument_types
from torch.nn.utils.rnn import pad_sequence
+from typeguard import check_argument_types
+
+import funasr.models.frontend.eend_ola_feature as eend_ola_feature
+from funasr.models.frontend.abs_frontend import AbsFrontend
def load_cmvn(cmvn_file):
@@ -275,7 +276,8 @@
# inputs tensor has catted the cache tensor
# def apply_lfr(inputs: torch.Tensor, lfr_m: int, lfr_n: int, inputs_lfr_cache: torch.Tensor = None,
# is_final: bool = False) -> Tuple[torch.Tensor, torch.Tensor, int]:
- def apply_lfr(inputs: torch.Tensor, lfr_m: int, lfr_n: int, is_final: bool = False) -> Tuple[torch.Tensor, torch.Tensor, int]:
+ def apply_lfr(inputs: torch.Tensor, lfr_m: int, lfr_n: int, is_final: bool = False) -> Tuple[
+ torch.Tensor, torch.Tensor, int]:
"""
Apply lfr with data
"""
@@ -376,7 +378,8 @@
if self.lfr_m != 1 or self.lfr_n != 1:
# update self.lfr_splice_cache in self.apply_lfr
# mat, self.lfr_splice_cache[i], lfr_splice_frame_idx = self.apply_lfr(mat, self.lfr_m, self.lfr_n, self.lfr_splice_cache[i],
- mat, self.lfr_splice_cache[i], lfr_splice_frame_idx = self.apply_lfr(mat, self.lfr_m, self.lfr_n, is_final)
+ mat, self.lfr_splice_cache[i], lfr_splice_frame_idx = self.apply_lfr(mat, self.lfr_m, self.lfr_n,
+ is_final)
if self.cmvn_file is not None:
mat = self.apply_cmvn(mat, self.cmvn)
feat_length = mat.size(0)
@@ -398,9 +401,10 @@
assert batch_size == 1, 'we support to extract feature online only when the batch size is equal to 1 now'
waveforms, feats, feats_lengths = self.forward_fbank(input, input_lengths) # input shape: B T D
if feats.shape[0]:
- #if self.reserve_waveforms is None and self.lfr_m > 1:
+ # if self.reserve_waveforms is None and self.lfr_m > 1:
# self.reserve_waveforms = waveforms[:, :(self.lfr_m - 1) // 2 * self.frame_shift_sample_length]
- self.waveforms = waveforms if self.reserve_waveforms is None else torch.cat((self.reserve_waveforms, waveforms), dim=1)
+ self.waveforms = waveforms if self.reserve_waveforms is None else torch.cat(
+ (self.reserve_waveforms, waveforms), dim=1)
if not self.lfr_splice_cache: # 鍒濆鍖杝plice_cache
for i in range(batch_size):
self.lfr_splice_cache.append(feats[i][0, :].unsqueeze(dim=0).repeat((self.lfr_m - 1) // 2, 1))
@@ -409,7 +413,8 @@
lfr_splice_cache_tensor = torch.stack(self.lfr_splice_cache) # B T D
feats = torch.cat((lfr_splice_cache_tensor, feats), dim=1)
feats_lengths += lfr_splice_cache_tensor[0].shape[0]
- frame_from_waveforms = int((self.waveforms.shape[1] - self.frame_sample_length) / self.frame_shift_sample_length + 1)
+ frame_from_waveforms = int(
+ (self.waveforms.shape[1] - self.frame_sample_length) / self.frame_shift_sample_length + 1)
minus_frame = (self.lfr_m - 1) // 2 if self.reserve_waveforms is None else 0
feats, feats_lengths, lfr_splice_frame_idxs = self.forward_lfr_cmvn(feats, feats_lengths, is_final)
if self.lfr_m == 1:
@@ -423,14 +428,15 @@
self.waveforms = self.waveforms[:, :sample_length]
else:
# update self.reserve_waveforms and self.lfr_splice_cache
- self.reserve_waveforms = self.waveforms[:, :-(self.frame_sample_length - self.frame_shift_sample_length)]
+ self.reserve_waveforms = self.waveforms[:,
+ :-(self.frame_sample_length - self.frame_shift_sample_length)]
for i in range(batch_size):
self.lfr_splice_cache[i] = torch.cat((self.lfr_splice_cache[i], feats[i]), dim=0)
return torch.empty(0), feats_lengths
else:
if is_final:
self.waveforms = waveforms if self.reserve_waveforms is None else self.reserve_waveforms
- feats = torch.stack(self.lfr_splice_cache)
+ feats = torch.stack(self.lfr_splice_cache)
feats_lengths = torch.zeros(batch_size, dtype=torch.int) + feats.shape[1]
feats, feats_lengths, _ = self.forward_lfr_cmvn(feats, feats_lengths, is_final)
if is_final:
@@ -444,3 +450,54 @@
self.reserve_waveforms = None
self.input_cache = None
self.lfr_splice_cache = []
+
+
+class WavFrontendMel23(AbsFrontend):
+ """Conventional frontend structure for ASR.
+ """
+
+ def __init__(
+ self,
+ fs: int = 16000,
+ frame_length: int = 25,
+ frame_shift: int = 10,
+ lfr_m: int = 1,
+ lfr_n: int = 1,
+ ):
+ assert check_argument_types()
+ super().__init__()
+ self.fs = fs
+ self.frame_length = frame_length
+ self.frame_shift = frame_shift
+ self.lfr_m = lfr_m
+ self.lfr_n = lfr_n
+ self.n_mels = 23
+
+ def output_size(self) -> int:
+ return self.n_mels * (2 * self.lfr_m + 1)
+
+ def forward(
+ self,
+ input: torch.Tensor,
+ input_lengths: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
+ batch_size = input.size(0)
+ feats = []
+ feats_lens = []
+ for i in range(batch_size):
+ waveform_length = input_lengths[i]
+ waveform = input[i][:waveform_length]
+ waveform = waveform.numpy()
+ mat = eend_ola_feature.stft(waveform, self.frame_length, self.frame_shift)
+ mat = eend_ola_feature.transform(mat)
+ mat = eend_ola_feature.splice(mat, context_size=self.lfr_m)
+ mat = mat[::self.lfr_n]
+ mat = torch.from_numpy(mat)
+ feat_length = mat.size(0)
+ feats.append(mat)
+ feats_lens.append(feat_length)
+
+ feats_lens = torch.as_tensor(feats_lens)
+ feats_pad = pad_sequence(feats,
+ batch_first=True,
+ padding_value=0.0)
+ return feats_pad, feats_lens
diff --git a/funasr/modules/eend_ola/encoder.py b/funasr/modules/eend_ola/encoder.py
index 4999031..90a63f3 100644
--- a/funasr/modules/eend_ola/encoder.py
+++ b/funasr/modules/eend_ola/encoder.py
@@ -87,7 +87,7 @@
n_layers: int,
n_units: int,
e_units: int = 2048,
- h: int = 8,
+ h: int = 4,
dropout_rate: float = 0.1,
use_pos_emb: bool = False):
super(EENDOLATransformerEncoder, self).__init__()
diff --git a/funasr/modules/eend_ola/encoder_decoder_attractor.py b/funasr/modules/eend_ola/encoder_decoder_attractor.py
index db01b00..45ac982 100644
--- a/funasr/modules/eend_ola/encoder_decoder_attractor.py
+++ b/funasr/modules/eend_ola/encoder_decoder_attractor.py
@@ -16,12 +16,12 @@
self.n_units = n_units
def forward_core(self, xs, zeros):
- ilens = torch.from_numpy(np.array([x.shape[0] for x in xs])).to(torch.float32).to(xs[0].device)
+ ilens = torch.from_numpy(np.array([x.shape[0] for x in xs])).to(torch.int64)
xs = [self.enc0_dropout(x) for x in xs]
xs = nn.utils.rnn.pad_sequence(xs, batch_first=True, padding_value=-1)
xs = nn.utils.rnn.pack_padded_sequence(xs, ilens, batch_first=True, enforce_sorted=False)
_, (hx, cx) = self.encoder(xs)
- zlens = torch.from_numpy(np.array([z.shape[0] for z in zeros])).to(torch.float32).to(zeros[0].device)
+ zlens = torch.from_numpy(np.array([z.shape[0] for z in zeros])).to(torch.int64)
max_zlen = torch.max(zlens).to(torch.int).item()
zeros = [self.enc0_dropout(z) for z in zeros]
zeros = nn.utils.rnn.pad_sequence(zeros, batch_first=True, padding_value=-1)
@@ -47,4 +47,4 @@
zeros = [torch.zeros(max_n_speakers, self.n_units).to(torch.float32).to(xs[0].device) for _ in xs]
attractors = self.forward_core(xs, zeros)
probs = [torch.sigmoid(torch.flatten(self.counter(att))) for att in attractors]
- return attractors, probs
\ No newline at end of file
+ return attractors, probs
diff --git a/funasr/runtime/onnxruntime/src/Audio.cpp b/funasr/runtime/onnxruntime/src/Audio.cpp
index 43dfb6b..53bf9d0 100644
--- a/funasr/runtime/onnxruntime/src/Audio.cpp
+++ b/funasr/runtime/onnxruntime/src/Audio.cpp
@@ -237,7 +237,7 @@
size_t nOffset = 0;
-#define WAV_HEADER_SIZE 44
+
speech_len = nBufLen / 2;
speech_align_len = (int)(ceil((float)speech_len / align_size) * align_size);
@@ -263,7 +263,8 @@
speech_data[i] = (float)speech_buff[i] / scale;
}
-
+ AudioFrame* frame = new AudioFrame(speech_len);
+ frame_queue.push(frame);
return true;
}
diff --git a/funasr/runtime/onnxruntime/src/librapidasrapi.cpp b/funasr/runtime/onnxruntime/src/librapidasrapi.cpp
index 1f8f7ca..f5f9d66 100644
--- a/funasr/runtime/onnxruntime/src/librapidasrapi.cpp
+++ b/funasr/runtime/onnxruntime/src/librapidasrapi.cpp
@@ -26,8 +26,9 @@
return nullptr;
Audio audio(1);
- audio.loadwav(szBuf,nLen);
- audio.split();
+ if (!audio.loadwav(szBuf, nLen))
+ return nullptr;
+ //audio.split();
float* buff;
int len;
@@ -58,8 +59,9 @@
return nullptr;
Audio audio(1);
- audio.loadpcmwav(szBuf, nLen);
- audio.split();
+ if (!audio.loadpcmwav(szBuf, nLen))
+ return nullptr;
+ //audio.split();
float* buff;
int len;
@@ -91,8 +93,9 @@
return nullptr;
Audio audio(1);
- audio.loadpcmwav(szFileName);
- audio.split();
+ if (!audio.loadpcmwav(szFileName))
+ return nullptr;
+ //audio.split();
float* buff;
int len;
@@ -125,7 +128,7 @@
Audio audio(1);
if(!audio.loadwav(szWavfile))
return nullptr;
- audio.split();
+ //audio.split();
float* buff;
int len;
diff --git a/funasr/runtime/onnxruntime/tester/tester.cpp b/funasr/runtime/onnxruntime/tester/tester.cpp
index b9a85b7..ba5c61c 100644
--- a/funasr/runtime/onnxruntime/tester/tester.cpp
+++ b/funasr/runtime/onnxruntime/tester/tester.cpp
@@ -8,7 +8,7 @@
#include "librapidasrapi.h"
#include <iostream>
-
+#include <fstream>
using namespace std;
int main(int argc, char *argv[])
@@ -40,10 +40,13 @@
gettimeofday(&start, NULL);
-
- RPASR_RESULT Result=RapidAsrRecogPCMFile(AsrHanlde, argv[2], RASR_NONE, NULL);
- gettimeofday(&end, NULL);
float snippet_time = 0.0f;
+
+
+ RPASR_RESULT Result=RapidAsrRecogFile(AsrHanlde, argv[2], RASR_NONE, NULL);
+
+ gettimeofday(&end, NULL);
+
if (Result)
{
string msg = RapidAsrGetResult(Result, 0);
@@ -56,11 +59,51 @@
}
else
{
- cout <<("no return data!");
+ cout <<"no return data!";
}
-
- printf("Audio length %lfs.\n", (double)snippet_time);
+
+
+ //char* buff = nullptr;
+ //int len = 0;
+ //ifstream ifs(argv[2], std::ios::binary | std::ios::in);
+ //if (ifs.is_open())
+ //{
+ // ifs.seekg(0, std::ios::end);
+ // len = ifs.tellg();
+ // ifs.seekg(0, std::ios::beg);
+ // buff = new char[len];
+
+ // ifs.read(buff, len);
+
+
+ // //RPASR_RESULT Result = RapidAsrRecogPCMFile(AsrHanlde, argv[2], RASR_NONE, NULL);
+
+ // RPASR_RESULT Result=RapidAsrRecogPCMBuffer(AsrHanlde, buff,len, RASR_NONE, NULL);
+ // //RPASR_RESULT Result = RapidAsrRecogPCMFile(AsrHanlde, argv[2], RASR_NONE, NULL);
+ // gettimeofday(&end, NULL);
+ //
+ // if (Result)
+ // {
+ // string msg = RapidAsrGetResult(Result, 0);
+ // setbuf(stdout, NULL);
+ // cout << "Result: \"";
+ // cout << msg << endl;
+ // cout << "\"." << endl;
+ // snippet_time = RapidAsrGetRetSnippetTime(Result);
+ // RapidAsrFreeResult(Result);
+ // }
+ // else
+ // {
+ // cout <<"no return data!";
+ // }
+
+ //
+ //delete[]buff;
+ //}
+
+
+ printf("Audio length %lfs.\n", (double)snippet_time);
seconds = (end.tv_sec - start.tv_sec);
long taking_micros = ((seconds * 1000000) + end.tv_usec) - (start.tv_usec);
printf("Model inference takes %lfs.\n", (double)taking_micros / 1000000);
diff --git a/funasr/runtime/python/README.md b/funasr/runtime/python/README.md
new file mode 100644
index 0000000..c47f8e7
--- /dev/null
+++ b/funasr/runtime/python/README.md
@@ -0,0 +1,21 @@
+Benchmark [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) based on Aishell1 test set , the total audio duration is 36108.919 seconds.
+
+(Note: The service has been fully warm up.)
+
+ Intel(R) Xeon(R) Platinum 8369B CPU @ 2.90GHz 16core-32processor with avx512_vnni
+
+| concurrent-tasks | processing time(s) | RTF | Speedup Rate |
+|:----------------:|:------------------:|:------:|:------------:|
+| 1 (onnx fp32) | 2806 | 0.0777 | 12.9 |
+| 1 (onnx int8) | 1611 | 0.0446 | 22.4 |
+| 8 (onnx fp32) | 538 | 0.0149 | 67.1 |
+| 8 (onnx int8) | 210 | 0.0058 | 172.4 |
+| 16 (onnx fp32) | 288 | 0.0080 | 125.2 |
+| 16 (onnx int8) | 117 | 0.0032 | 309.9 |
+| 32 (onnx fp32) | 167 | 0.0046 | 216.5 |
+| 32 (onnx int8) | 107 | 0.0030 | 338.0 |
+| 64 (onnx fp32) | 158 | 0.0044 | 228.1 |
+| 64 (onnx int8) | 82 | 0.0023 | 442.8 |
+| 96 (onnx fp32) | 151 | 0.0042 | 238.0 |
+| 96 (onnx int8) | 80 | 0.0022 | 452.0 |
+
diff --git a/funasr/tasks/abs_task.py b/funasr/tasks/abs_task.py
index e0884ce..3f20b4f 100644
--- a/funasr/tasks/abs_task.py
+++ b/funasr/tasks/abs_task.py
@@ -639,12 +639,12 @@
"and exclude_keys excludes keys of model states for the initialization."
"e.g.\n"
" # Load all parameters"
- " --init_param some/where/model.pth\n"
+ " --init_param some/where/model.pb\n"
" # Load only decoder parameters"
- " --init_param some/where/model.pth:decoder:decoder\n"
+ " --init_param some/where/model.pb:decoder:decoder\n"
" # Load only decoder parameters excluding decoder.embed"
- " --init_param some/where/model.pth:decoder:decoder:decoder.embed\n"
- " --init_param some/where/model.pth:decoder:decoder:decoder.embed\n",
+ " --init_param some/where/model.pb:decoder:decoder:decoder.embed\n"
+ " --init_param some/where/model.pb:decoder:decoder:decoder.embed\n",
)
group.add_argument(
"--ignore_init_mismatch",
diff --git a/funasr/tasks/asr.py b/funasr/tasks/asr.py
index 36499a2..e151473 100644
--- a/funasr/tasks/asr.py
+++ b/funasr/tasks/asr.py
@@ -826,7 +826,7 @@
if "model.ckpt-" in model_name or ".bin" in model_name:
model_name_pth = os.path.join(model_dir, model_name.replace('.bin',
'.pb')) if ".bin" in model_name else os.path.join(
- model_dir, "{}.pth".format(model_name))
+ model_dir, "{}.pb".format(model_name))
if os.path.exists(model_name_pth):
logging.info("model_file is load from pth: {}".format(model_name_pth))
model_dict = torch.load(model_name_pth, map_location=device)
@@ -1073,7 +1073,7 @@
if "model.ckpt-" in model_name or ".bin" in model_name:
model_name_pth = os.path.join(model_dir, model_name.replace('.bin',
'.pb')) if ".bin" in model_name else os.path.join(
- model_dir, "{}.pth".format(model_name))
+ model_dir, "{}.pb".format(model_name))
if os.path.exists(model_name_pth):
logging.info("model_file is load from pth: {}".format(model_name_pth))
model_dict = torch.load(model_name_pth, map_location=device)
diff --git a/funasr/tasks/diar.py b/funasr/tasks/diar.py
index ae7ee9b..9875f6a 100644
--- a/funasr/tasks/diar.py
+++ b/funasr/tasks/diar.py
@@ -553,7 +553,7 @@
if ".bin" in model_name:
model_name_pth = os.path.join(model_dir, model_name.replace('.bin', '.pb'))
else:
- model_name_pth = os.path.join(model_dir, "{}.pth".format(model_name))
+ model_name_pth = os.path.join(model_dir, "{}.pb".format(model_name))
if os.path.exists(model_name_pth):
logging.info("model_file is load from pth: {}".format(model_name_pth))
model_dict = torch.load(model_name_pth, map_location=device)
@@ -750,47 +750,47 @@
cls, args: argparse.Namespace, train: bool
) -> Optional[Callable[[str, Dict[str, np.array]], Dict[str, np.ndarray]]]:
assert check_argument_types()
- if args.use_preprocessor:
- retval = CommonPreprocessor(
- train=train,
- token_type=args.token_type,
- token_list=args.token_list,
- bpemodel=None,
- non_linguistic_symbols=None,
- text_cleaner=None,
- g2p_type=None,
- split_with_space=args.split_with_space if hasattr(args, "split_with_space") else False,
- seg_dict_file=args.seg_dict_file if hasattr(args, "seg_dict_file") else None,
- # NOTE(kamo): Check attribute existence for backward compatibility
- rir_scp=args.rir_scp if hasattr(args, "rir_scp") else None,
- rir_apply_prob=args.rir_apply_prob
- if hasattr(args, "rir_apply_prob")
- else 1.0,
- noise_scp=args.noise_scp if hasattr(args, "noise_scp") else None,
- noise_apply_prob=args.noise_apply_prob
- if hasattr(args, "noise_apply_prob")
- else 1.0,
- noise_db_range=args.noise_db_range
- if hasattr(args, "noise_db_range")
- else "13_15",
- speech_volume_normalize=args.speech_volume_normalize
- if hasattr(args, "rir_scp")
- else None,
- )
- else:
- retval = None
- assert check_return_type(retval)
- return retval
+ # if args.use_preprocessor:
+ # retval = CommonPreprocessor(
+ # train=train,
+ # token_type=args.token_type,
+ # token_list=args.token_list,
+ # bpemodel=None,
+ # non_linguistic_symbols=None,
+ # text_cleaner=None,
+ # g2p_type=None,
+ # split_with_space=args.split_with_space if hasattr(args, "split_with_space") else False,
+ # seg_dict_file=args.seg_dict_file if hasattr(args, "seg_dict_file") else None,
+ # # NOTE(kamo): Check attribute existence for backward compatibility
+ # rir_scp=args.rir_scp if hasattr(args, "rir_scp") else None,
+ # rir_apply_prob=args.rir_apply_prob
+ # if hasattr(args, "rir_apply_prob")
+ # else 1.0,
+ # noise_scp=args.noise_scp if hasattr(args, "noise_scp") else None,
+ # noise_apply_prob=args.noise_apply_prob
+ # if hasattr(args, "noise_apply_prob")
+ # else 1.0,
+ # noise_db_range=args.noise_db_range
+ # if hasattr(args, "noise_db_range")
+ # else "13_15",
+ # speech_volume_normalize=args.speech_volume_normalize
+ # if hasattr(args, "rir_scp")
+ # else None,
+ # )
+ # else:
+ # retval = None
+ # assert check_return_type(retval)
+ return None
@classmethod
def required_data_names(
cls, train: bool = True, inference: bool = False
) -> Tuple[str, ...]:
if not inference:
- retval = ("speech", "profile", "binary_labels")
+ retval = ("speech", )
else:
# Recognition mode
- retval = ("speech")
+ retval = ("speech", )
return retval
@classmethod
@@ -823,7 +823,7 @@
# 2. Encoder
encoder_class = encoder_choices.get_class(args.encoder)
- encoder = encoder_class(input_size=input_size, **args.encoder_conf)
+ encoder = encoder_class(**args.encoder_conf)
# 3. EncoderDecoderAttractor
encoder_decoder_attractor_class = encoder_decoder_attractor_choices.get_class(args.encoder_decoder_attractor)
diff --git a/funasr/tasks/sv.py b/funasr/tasks/sv.py
index 1b08c4d..bef5dc5 100644
--- a/funasr/tasks/sv.py
+++ b/funasr/tasks/sv.py
@@ -501,7 +501,7 @@
if ".bin" in model_name:
model_name_pth = os.path.join(model_dir, model_name.replace('.bin', '.pb'))
else:
- model_name_pth = os.path.join(model_dir, "{}.pth".format(model_name))
+ model_name_pth = os.path.join(model_dir, "{}.pb".format(model_name))
if os.path.exists(model_name_pth):
logging.info("model_file is load from pth: {}".format(model_name_pth))
model_dict = torch.load(model_name_pth, map_location=device)
diff --git a/funasr/torch_utils/load_pretrained_model.py b/funasr/torch_utils/load_pretrained_model.py
index 8e3f05e..e9b18cd 100644
--- a/funasr/torch_utils/load_pretrained_model.py
+++ b/funasr/torch_utils/load_pretrained_model.py
@@ -52,13 +52,13 @@
init_param: <file_path>:<src_key>:<dst_key>:<exclude_Keys>
Examples:
- >>> load_pretrained_model("somewhere/model.pth", model)
- >>> load_pretrained_model("somewhere/model.pth:decoder:decoder", model)
- >>> load_pretrained_model("somewhere/model.pth:decoder:decoder:", model)
+ >>> load_pretrained_model("somewhere/model.pb", model)
+ >>> load_pretrained_model("somewhere/model.pb:decoder:decoder", model)
+ >>> load_pretrained_model("somewhere/model.pb:decoder:decoder:", model)
>>> load_pretrained_model(
- ... "somewhere/model.pth:decoder:decoder:decoder.embed", model
+ ... "somewhere/model.pb:decoder:decoder:decoder.embed", model
... )
- >>> load_pretrained_model("somewhere/decoder.pth::decoder", model)
+ >>> load_pretrained_model("somewhere/decoder.pb::decoder", model)
"""
sps = init_param.split(":", 4)
if len(sps) == 4:
diff --git a/funasr/train/trainer.py b/funasr/train/trainer.py
index 50bce47..efe2009 100644
--- a/funasr/train/trainer.py
+++ b/funasr/train/trainer.py
@@ -205,9 +205,9 @@
else:
scaler = None
- if trainer_options.resume and (output_dir / "checkpoint.pth").exists():
+ if trainer_options.resume and (output_dir / "checkpoint.pb").exists():
cls.resume(
- checkpoint=output_dir / "checkpoint.pth",
+ checkpoint=output_dir / "checkpoint.pb",
model=model,
optimizers=optimizers,
schedulers=schedulers,
@@ -361,7 +361,7 @@
},
buffer,
)
- trainer_options.oss_bucket.put_object(os.path.join(trainer_options.output_dir, "checkpoint.pth"), buffer.getvalue())
+ trainer_options.oss_bucket.put_object(os.path.join(trainer_options.output_dir, "checkpoint.pb"), buffer.getvalue())
else:
torch.save(
{
@@ -374,7 +374,7 @@
],
"scaler": scaler.state_dict() if scaler is not None else None,
},
- output_dir / "checkpoint.pth",
+ output_dir / "checkpoint.pb",
)
# 5. Save and log the model and update the link to the best model
@@ -382,22 +382,22 @@
buffer = BytesIO()
torch.save(model.state_dict(), buffer)
trainer_options.oss_bucket.put_object(os.path.join(trainer_options.output_dir,
- f"{iepoch}epoch.pth"),buffer.getvalue())
+ f"{iepoch}epoch.pb"),buffer.getvalue())
else:
- torch.save(model.state_dict(), output_dir / f"{iepoch}epoch.pth")
+ torch.save(model.state_dict(), output_dir / f"{iepoch}epoch.pb")
- # Creates a sym link latest.pth -> {iepoch}epoch.pth
+ # Creates a sym link latest.pb -> {iepoch}epoch.pb
if trainer_options.use_pai:
- p = os.path.join(trainer_options.output_dir, "latest.pth")
+ p = os.path.join(trainer_options.output_dir, "latest.pb")
if trainer_options.oss_bucket.object_exists(p):
trainer_options.oss_bucket.delete_object(p)
trainer_options.oss_bucket.copy_object(trainer_options.oss_bucket.bucket_name,
- os.path.join(trainer_options.output_dir, f"{iepoch}epoch.pth"), p)
+ os.path.join(trainer_options.output_dir, f"{iepoch}epoch.pb"), p)
else:
- p = output_dir / "latest.pth"
+ p = output_dir / "latest.pb"
if p.is_symlink() or p.exists():
p.unlink()
- p.symlink_to(f"{iepoch}epoch.pth")
+ p.symlink_to(f"{iepoch}epoch.pb")
_improved = []
for _phase, k, _mode in trainer_options.best_model_criterion:
@@ -407,16 +407,16 @@
# Creates sym links if it's the best result
if best_epoch == iepoch:
if trainer_options.use_pai:
- p = os.path.join(trainer_options.output_dir, f"{_phase}.{k}.best.pth")
+ p = os.path.join(trainer_options.output_dir, f"{_phase}.{k}.best.pb")
if trainer_options.oss_bucket.object_exists(p):
trainer_options.oss_bucket.delete_object(p)
trainer_options.oss_bucket.copy_object(trainer_options.oss_bucket.bucket_name,
- os.path.join(trainer_options.output_dir, f"{iepoch}epoch.pth"),p)
+ os.path.join(trainer_options.output_dir, f"{iepoch}epoch.pb"),p)
else:
- p = output_dir / f"{_phase}.{k}.best.pth"
+ p = output_dir / f"{_phase}.{k}.best.pb"
if p.is_symlink() or p.exists():
p.unlink()
- p.symlink_to(f"{iepoch}epoch.pth")
+ p.symlink_to(f"{iepoch}epoch.pb")
_improved.append(f"{_phase}.{k}")
if len(_improved) == 0:
logging.info("There are no improvements in this epoch")
@@ -438,7 +438,7 @@
type="model",
metadata={"improved": _improved},
)
- artifact.add_file(str(output_dir / f"{iepoch}epoch.pth"))
+ artifact.add_file(str(output_dir / f"{iepoch}epoch.pb"))
aliases = [
f"epoch-{iepoch}",
"best" if best_epoch == iepoch else "",
@@ -473,12 +473,12 @@
for e in range(1, iepoch):
if trainer_options.use_pai:
- p = os.path.join(trainer_options.output_dir, f"{e}epoch.pth")
+ p = os.path.join(trainer_options.output_dir, f"{e}epoch.pb")
if trainer_options.oss_bucket.object_exists(p) and e not in nbests:
trainer_options.oss_bucket.delete_object(p)
_removed.append(str(p))
else:
- p = output_dir / f"{e}epoch.pth"
+ p = output_dir / f"{e}epoch.pb"
if p.exists() and e not in nbests:
p.unlink()
_removed.append(str(p))
diff --git a/funasr/utils/timestamp_tools.py b/funasr/utils/timestamp_tools.py
index f5a238e..423110c 100644
--- a/funasr/utils/timestamp_tools.py
+++ b/funasr/utils/timestamp_tools.py
@@ -1,6 +1,10 @@
import torch
import copy
+import codecs
import logging
+import edit_distance
+import argparse
+import pdb
import numpy as np
from typing import Any, List, Tuple, Union
@@ -9,7 +13,8 @@
us_peaks,
char_list,
vad_offset=0.0,
- force_time_shift=-1.5
+ force_time_shift=-1.5,
+ sil_in_str=True
):
if not len(char_list):
return []
@@ -62,6 +67,8 @@
timestamp_list[i][1] = timestamp_list[i][1] + vad_offset / 1000.0
res_txt = ""
for char, timestamp in zip(new_char_list, timestamp_list):
+ #if char != '<sil>':
+ if not sil_in_str and char == '<sil>': continue
res_txt += "{} {} {};".format(char, str(timestamp[0]+0.0005)[:5], str(timestamp[1]+0.0005)[:5])
res = []
for char, timestamp in zip(new_char_list, timestamp_list):
@@ -121,4 +128,181 @@
return res
+class AverageShiftCalculator():
+ def __init__(self):
+ logging.warning("Calculating average shift.")
+ def __call__(self, file1, file2):
+ uttid_list1, ts_dict1 = self.read_timestamps(file1)
+ uttid_list2, ts_dict2 = self.read_timestamps(file2)
+ uttid_intersection = self._intersection(uttid_list1, uttid_list2)
+ res = self.as_cal(uttid_intersection, ts_dict1, ts_dict2)
+ logging.warning("Average shift of {} and {}: {}.".format(file1, file2, str(res)[:8]))
+ logging.warning("Following timestamp pair differs most: {}, detail:{}".format(self.max_shift, self.max_shift_uttid))
+
+ def _intersection(self, list1, list2):
+ set1 = set(list1)
+ set2 = set(list2)
+ if set1 == set2:
+ logging.warning("Uttid same checked.")
+ return set1
+ itsc = list(set1 & set2)
+ logging.warning("Uttid differs: file1 {}, file2 {}, lines same {}.".format(len(list1), len(list2), len(itsc)))
+ return itsc
+
+ def read_timestamps(self, file):
+ # read timestamps file in standard format
+ uttid_list = []
+ ts_dict = {}
+ with codecs.open(file, 'r') as fin:
+ for line in fin.readlines():
+ text = ''
+ ts_list = []
+ line = line.rstrip()
+ uttid = line.split()[0]
+ uttid_list.append(uttid)
+ body = " ".join(line.split()[1:])
+ for pd in body.split(';'):
+ if not len(pd): continue
+ # pdb.set_trace()
+ char, start, end = pd.lstrip(" ").split(' ')
+ text += char + ','
+ ts_list.append((float(start), float(end)))
+ # ts_lists.append(ts_list)
+ ts_dict[uttid] = (text[:-1], ts_list)
+ logging.warning("File {} read done.".format(file))
+ return uttid_list, ts_dict
+
+ def _shift(self, filtered_timestamp_list1, filtered_timestamp_list2):
+ shift_time = 0
+ for fts1, fts2 in zip(filtered_timestamp_list1, filtered_timestamp_list2):
+ shift_time += abs(fts1[0] - fts2[0]) + abs(fts1[1] - fts2[1])
+ num_tokens = len(filtered_timestamp_list1)
+ return shift_time, num_tokens
+
+ def as_cal(self, uttid_list, ts_dict1, ts_dict2):
+ # calculate average shift between timestamp1 and timestamp2
+ # when characters differ, use edit distance alignment
+ # and calculate the error between the same characters
+ self._accumlated_shift = 0
+ self._accumlated_tokens = 0
+ self.max_shift = 0
+ self.max_shift_uttid = None
+ for uttid in uttid_list:
+ (t1, ts1) = ts_dict1[uttid]
+ (t2, ts2) = ts_dict2[uttid]
+ _align, _align2, _align3 = [], [], []
+ fts1, fts2 = [], []
+ _t1, _t2 = [], []
+ sm = edit_distance.SequenceMatcher(t1.split(','), t2.split(','))
+ s = sm.get_opcodes()
+ for j in range(len(s)):
+ if s[j][0] == "replace" or s[j][0] == "insert":
+ _align.append(0)
+ if s[j][0] == "replace" or s[j][0] == "delete":
+ _align3.append(0)
+ elif s[j][0] == "equal":
+ _align.append(1)
+ _align3.append(1)
+ else:
+ continue
+ # use s to index t2
+ for a, ts , t in zip(_align, ts2, t2.split(',')):
+ if a:
+ fts2.append(ts)
+ _t2.append(t)
+ sm2 = edit_distance.SequenceMatcher(t2.split(','), t1.split(','))
+ s = sm2.get_opcodes()
+ for j in range(len(s)):
+ if s[j][0] == "replace" or s[j][0] == "insert":
+ _align2.append(0)
+ elif s[j][0] == "equal":
+ _align2.append(1)
+ else:
+ continue
+ # use s2 tp index t1
+ for a, ts, t in zip(_align3, ts1, t1.split(',')):
+ if a:
+ fts1.append(ts)
+ _t1.append(t)
+ if len(fts1) == len(fts2):
+ shift_time, num_tokens = self._shift(fts1, fts2)
+ self._accumlated_shift += shift_time
+ self._accumlated_tokens += num_tokens
+ if shift_time/num_tokens > self.max_shift:
+ self.max_shift = shift_time/num_tokens
+ self.max_shift_uttid = uttid
+ else:
+ logging.warning("length mismatch")
+ return self._accumlated_shift / self._accumlated_tokens
+
+
+def convert_external_alphas(alphas_file, text_file, output_file):
+ from funasr.models.predictor.cif import cif_wo_hidden
+ with open(alphas_file, 'r') as f1, open(text_file, 'r') as f2, open(output_file, 'w') as f3:
+ for line1, line2 in zip(f1.readlines(), f2.readlines()):
+ line1 = line1.rstrip()
+ line2 = line2.rstrip()
+ assert line1.split()[0] == line2.split()[0]
+ uttid = line1.split()[0]
+ alphas = [float(i) for i in line1.split()[1:]]
+ new_alphas = np.array(remove_chunk_padding(alphas))
+ new_alphas[-1] += 1e-4
+ text = line2.split()[1:]
+ if len(text) + 1 != int(new_alphas.sum()):
+ # force resize
+ new_alphas *= (len(text) + 1) / int(new_alphas.sum())
+ peaks = cif_wo_hidden(torch.Tensor(new_alphas).unsqueeze(0), 1.0-1e-4)
+ if " " in text:
+ text = text.split()
+ else:
+ text = [i for i in text]
+ res_str, _ = ts_prediction_lfr6_standard(new_alphas, peaks[0], text,
+ force_time_shift=-7.0,
+ sil_in_str=False)
+ f3.write("{} {}\n".format(uttid, res_str))
+
+
+def remove_chunk_padding(alphas):
+ # remove the padding part in alphas if using chunk paraformer for GPU
+ START_ZERO = 45
+ MID_ZERO = 75
+ REAL_FRAMES = 360 # for chunk based encoder 10-120-10 and fsmn padding 5
+ alphas = alphas[START_ZERO:] # remove the padding at beginning
+ new_alphas = []
+ while True:
+ new_alphas = new_alphas + alphas[:REAL_FRAMES]
+ alphas = alphas[REAL_FRAMES+MID_ZERO:]
+ if len(alphas) < REAL_FRAMES: break
+ return new_alphas
+
+SUPPORTED_MODES = ['cal_aas', 'read_ext_alphas']
+
+
+def main(args):
+ if args.mode == 'cal_aas':
+ asc = AverageShiftCalculator()
+ asc(args.input, args.input2)
+ elif args.mode == 'read_ext_alphas':
+ convert_external_alphas(args.input, args.input2, args.output)
+ else:
+ logging.error("Mode {} not in SUPPORTED_MODES: {}.".format(args.mode, SUPPORTED_MODES))
+
+
+if __name__ == '__main__':
+ parser = argparse.ArgumentParser(description='timestamp tools')
+ parser.add_argument('--mode',
+ default=None,
+ type=str,
+ choices=SUPPORTED_MODES,
+ help='timestamp related toolbox')
+ parser.add_argument('--input', default=None, type=str, help='input file path')
+ parser.add_argument('--output', default=None, type=str, help='output file name')
+ parser.add_argument('--input2', default=None, type=str, help='input2 file path')
+ parser.add_argument('--kaldi-ts-type',
+ default='v2',
+ type=str,
+ choices=['v0', 'v1', 'v2'],
+ help='kaldi timestamp to write')
+ args = parser.parse_args()
+ main(args)
diff --git a/setup.py b/setup.py
index 087d90d..c854769 100644
--- a/setup.py
+++ b/setup.py
@@ -17,7 +17,7 @@
"humanfriendly",
"scipy>=1.4.1",
# "filelock",
- "librosa>=0.8.0",
+ "librosa==0.8.1",
"jamo==0.4.1", # For kss
"PyYAML>=5.1.2",
"soundfile>=0.10.2",
@@ -41,6 +41,8 @@
# PAI
"oss2",
"kaldi-native-fbank",
+ # timestamp
+ "edit-distance"
],
# train: The modules invoked when training only.
"train": [
diff --git a/tests/test_asr_inference_pipeline.py b/tests/test_asr_inference_pipeline.py
index 70dbe89..32b8af5 100644
--- a/tests/test_asr_inference_pipeline.py
+++ b/tests/test_asr_inference_pipeline.py
@@ -451,7 +451,7 @@
def test_uniasr_2pass_zhcn_16k_common_vocab8358_offline(self):
inference_pipeline = pipeline(
- task=Tasks.,
+ task=Tasks.auto_speech_recognition,
model='damo/speech_UniASauto_speech_recognitionR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline')
rec_result = inference_pipeline(
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav',
--
Gitblit v1.9.1