From 4a71f20682f3d9a665cfb67afdaf673cc81d81b1 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 22 二月 2024 13:09:55 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR merge
---
funasr/version.txt | 2
.gitignore | 1
examples/aishell/transformer/demo_train_or_finetune.sh | 1
funasr/train_utils/trainer.py | 4
examples/industrial_data_pretraining/paraformer/finetune_from_local.sh | 61 ++++
examples/industrial_data_pretraining/paraformer/finetune.sh | 49 ++-
examples/aishell/e_branchformer/demo_train_or_finetune.sh | 1
examples/industrial_data_pretraining/fsmn_vad_streaming/demo.sh | 0
examples/industrial_data_pretraining/paraformer_streaming/demo.sh | 0
examples/aishell/e_branchformer/demo_infer.sh | 1
examples/aishell/paraformer/demo_train_or_finetune.sh | 51 +++
examples/industrial_data_pretraining/scama/demo.sh | 0
examples/industrial_data_pretraining/uniasr/demo.sh | 0
funasr/bin/train.py | 21
examples/industrial_data_pretraining/monotonic_aligner/demo.sh | 0
examples/industrial_data_pretraining/transducer/demo.py | 15 +
examples/aishell/branchformer/demo_infer.sh | 1
examples/aishell/paraformer/demo_infer.sh | 3
examples/aishell/conformer/demo_train_or_finetune.sh | 1
examples/aishell/transformer/demo_infer.sh | 1
examples/industrial_data_pretraining/contextual_paraformer/demo.sh | 0
examples/industrial_data_pretraining/ct_transformer_streaming/demo.sh | 0
examples/aishell/branchformer/demo_train_or_finetune.sh | 1
examples/industrial_data_pretraining/paraformer/infer.sh | 21 +
examples/industrial_data_pretraining/paraformer/infer_from_local.sh | 39 ++
funasr/models/bat/model.py | 488 ----------------------------------
README_zh.md | 2
funasr/train_utils/load_pretrained_model.py | 9
README.md | 2
/dev/null | 12
examples/industrial_data_pretraining/seaco_paraformer/demo.sh | 0
examples/industrial_data_pretraining/bicif_paraformer/demo.sh | 0
examples/industrial_data_pretraining/ct_transformer/demo.sh | 0
examples/industrial_data_pretraining/conformer/demo.sh | 0
examples/aishell/conformer/demo_infer.sh | 1
examples/industrial_data_pretraining/paraformer-zh-spk/demo.sh | 0
36 files changed, 257 insertions(+), 531 deletions(-)
diff --git a/.gitignore b/.gitignore
index 6bdfd5d..adf2937 100644
--- a/.gitignore
+++ b/.gitignore
@@ -24,3 +24,4 @@
outputs*
emotion2vec*
GPT-SoVITS*
+modelscope_models
diff --git a/README.md b/README.md
index bdedfb2..454adc9 100644
--- a/README.md
+++ b/README.md
@@ -95,7 +95,7 @@
### Command-line usage
```shell
-funasr +model=paraformer-zh +vad_model="fsmn-vad" +punc_model="ct-punc" +input=asr_example_zh.wav
+funasr ++model=paraformer-zh ++vad_model="fsmn-vad" ++punc_model="ct-punc" ++input=asr_example_zh.wav
```
Notes: Support recognition of single audio file, as well as file list in Kaldi-style wav.scp format: `wav_id wav_pat`
diff --git a/README_zh.md b/README_zh.md
index 5d9061b..07cdd1f 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -91,7 +91,7 @@
### 鍙墽琛屽懡浠よ
```shell
-funasr +model=paraformer-zh +vad_model="fsmn-vad" +punc_model="ct-punc" +input=asr_example_zh.wav
+funasr ++model=paraformer-zh ++vad_model="fsmn-vad" ++punc_model="ct-punc" ++input=asr_example_zh.wav
```
娉細鏀寔鍗曟潯闊抽鏂囦欢璇嗗埆锛屼篃鏀寔鏂囦欢鍒楄〃锛屽垪琛ㄤ负kaldi椋庢牸wav.scp锛歚wav_id wav_path`
diff --git a/examples/aishell/branchformer/demo_infer.sh b/examples/aishell/branchformer/demo_infer.sh
new file mode 120000
index 0000000..9d0a7a9
--- /dev/null
+++ b/examples/aishell/branchformer/demo_infer.sh
@@ -0,0 +1 @@
+../paraformer/demo_infer.sh
\ No newline at end of file
diff --git a/examples/aishell/branchformer/demo_train_or_finetune.sh b/examples/aishell/branchformer/demo_train_or_finetune.sh
new file mode 120000
index 0000000..bbabdbe
--- /dev/null
+++ b/examples/aishell/branchformer/demo_train_or_finetune.sh
@@ -0,0 +1 @@
+../paraformer/demo_train_or_finetune.sh
\ No newline at end of file
diff --git a/examples/aishell/conformer/demo_infer.sh b/examples/aishell/conformer/demo_infer.sh
new file mode 120000
index 0000000..9d0a7a9
--- /dev/null
+++ b/examples/aishell/conformer/demo_infer.sh
@@ -0,0 +1 @@
+../paraformer/demo_infer.sh
\ No newline at end of file
diff --git a/examples/aishell/conformer/demo_train_or_finetune.sh b/examples/aishell/conformer/demo_train_or_finetune.sh
new file mode 120000
index 0000000..bbabdbe
--- /dev/null
+++ b/examples/aishell/conformer/demo_train_or_finetune.sh
@@ -0,0 +1 @@
+../paraformer/demo_train_or_finetune.sh
\ No newline at end of file
diff --git a/examples/aishell/e_branchformer/demo_infer.sh b/examples/aishell/e_branchformer/demo_infer.sh
new file mode 120000
index 0000000..9d0a7a9
--- /dev/null
+++ b/examples/aishell/e_branchformer/demo_infer.sh
@@ -0,0 +1 @@
+../paraformer/demo_infer.sh
\ No newline at end of file
diff --git a/examples/aishell/e_branchformer/demo_train_or_finetune.sh b/examples/aishell/e_branchformer/demo_train_or_finetune.sh
new file mode 120000
index 0000000..bbabdbe
--- /dev/null
+++ b/examples/aishell/e_branchformer/demo_train_or_finetune.sh
@@ -0,0 +1 @@
+../paraformer/demo_train_or_finetune.sh
\ No newline at end of file
diff --git a/examples/aishell/e_branchformer/infer.sh b/examples/aishell/e_branchformer/infer.sh
deleted file mode 100644
index bcd4305..0000000
--- a/examples/aishell/e_branchformer/infer.sh
+++ /dev/null
@@ -1,12 +0,0 @@
-
-
-python -m funasr.bin.inference \
---config-path="/mnt/workspace/FunASR/examples/aishell/paraformer/exp/baseline_paraformer_conformer_12e_6d_2048_256_zh_char_exp3" \
---config-name="config.yaml" \
-++init_param="/mnt/workspace/FunASR/examples/aishell/paraformer/exp/baseline_paraformer_conformer_12e_6d_2048_256_zh_char_exp3/model.pt.ep38" \
-++tokenizer_conf.token_list="/mnt/nfs/zhifu.gzf/data/AISHELL-1-feats/DATA/data/zh_token_list/char/tokens.txt" \
-++frontend_conf.cmvn_file="/mnt/nfs/zhifu.gzf/data/AISHELL-1-feats/DATA/data/train/am.mvn" \
-++input="/mnt/nfs/zhifu.gzf/data/AISHELL-1/data_aishell/wav/train/S0002/BAC009S0002W0122.wav" \
-++output_dir="./outputs/debug" \
-++device="cuda:0" \
-
diff --git a/examples/aishell/conformer/infer.sh b/examples/aishell/paraformer/demo_infer.sh
similarity index 82%
rename from examples/aishell/conformer/infer.sh
rename to examples/aishell/paraformer/demo_infer.sh
index bcd4305..b3b989f 100644
--- a/examples/aishell/conformer/infer.sh
+++ b/examples/aishell/paraformer/demo_infer.sh
@@ -1,3 +1,6 @@
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+# MIT License (https://opensource.org/licenses/MIT)
+
python -m funasr.bin.inference \
diff --git a/examples/aishell/paraformer/demo_train_or_finetune.sh b/examples/aishell/paraformer/demo_train_or_finetune.sh
new file mode 100644
index 0000000..06607c7
--- /dev/null
+++ b/examples/aishell/paraformer/demo_train_or_finetune.sh
@@ -0,0 +1,51 @@
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+# MIT License (https://opensource.org/licenses/MIT)
+
+
+# which gpu to train or finetune
+export CUDA_VISIBLE_DEVICES="0,1"
+gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+
+# data dir, which contains: train.json, val.json, tokens.jsonl/tokens.txt, am.mvn
+data_dir="/Users/zhifu/funasr1.0/data/list"
+
+## generate jsonl from wav.scp and text.txt
+#python -m funasr.datasets.audio_datasets.scp2jsonl \
+#++scp_file_list='["/Users/zhifu/funasr1.0/test_local/wav.scp", "/Users/zhifu/funasr1.0/test_local/text.txt"]' \
+#++data_type_list='["source", "target"]' \
+#++jsonl_file_out=/Users/zhifu/funasr1.0/test_local/audio_datasets.jsonl
+
+train_data="${data_dir}/train.jsonl"
+val_data="${data_dir}/val.jsonl"
+tokens="${data_dir}/tokens.json"
+cmvn_file="${data_dir}/am.mvn"
+
+# exp output dir
+output_dir="/Users/zhifu/exp"
+log_file="${output_dir}/log.txt"
+
+workspace=`pwd`
+config="paraformer_conformer_12e_6d_2048_256.yaml"
+
+init_param="${output_dir}/model.pt"
+
+mkdir -p ${output_dir}
+echo "log_file: ${log_file}"
+
+torchrun \
+--nnodes 1 \
+--nproc_per_node ${gpu_num} \
+../../../funasr/bin/train.py \
+--config-path "${workspace}/conf" \
+--config-name "${config}" \
+++train_data_set_list="${train_data}" \
+++valid_data_set_list="${val_data}" \
+++tokenizer_conf.token_list="${tokens}" \
+++frontend_conf.cmvn_file="${cmvn_file}" \
+++dataset_conf.batch_size=32 \
+++dataset_conf.batch_type="example" \
+++dataset_conf.num_workers=4 \
+++train_conf.max_epoch=150 \
+++optim_conf.lr=0.0002 \
+++init_param="${init_param}" \
+++output_dir="${output_dir}" &> ${log_file}
diff --git a/examples/aishell/paraformer/infer.sh b/examples/aishell/paraformer/infer.sh
deleted file mode 100644
index bcd4305..0000000
--- a/examples/aishell/paraformer/infer.sh
+++ /dev/null
@@ -1,12 +0,0 @@
-
-
-python -m funasr.bin.inference \
---config-path="/mnt/workspace/FunASR/examples/aishell/paraformer/exp/baseline_paraformer_conformer_12e_6d_2048_256_zh_char_exp3" \
---config-name="config.yaml" \
-++init_param="/mnt/workspace/FunASR/examples/aishell/paraformer/exp/baseline_paraformer_conformer_12e_6d_2048_256_zh_char_exp3/model.pt.ep38" \
-++tokenizer_conf.token_list="/mnt/nfs/zhifu.gzf/data/AISHELL-1-feats/DATA/data/zh_token_list/char/tokens.txt" \
-++frontend_conf.cmvn_file="/mnt/nfs/zhifu.gzf/data/AISHELL-1-feats/DATA/data/train/am.mvn" \
-++input="/mnt/nfs/zhifu.gzf/data/AISHELL-1/data_aishell/wav/train/S0002/BAC009S0002W0122.wav" \
-++output_dir="./outputs/debug" \
-++device="cuda:0" \
-
diff --git a/examples/aishell/transformer/demo_infer.sh b/examples/aishell/transformer/demo_infer.sh
new file mode 120000
index 0000000..9d0a7a9
--- /dev/null
+++ b/examples/aishell/transformer/demo_infer.sh
@@ -0,0 +1 @@
+../paraformer/demo_infer.sh
\ No newline at end of file
diff --git a/examples/aishell/transformer/demo_train_or_finetune.sh b/examples/aishell/transformer/demo_train_or_finetune.sh
new file mode 120000
index 0000000..bbabdbe
--- /dev/null
+++ b/examples/aishell/transformer/demo_train_or_finetune.sh
@@ -0,0 +1 @@
+../paraformer/demo_train_or_finetune.sh
\ No newline at end of file
diff --git a/examples/aishell/transformer/infer.sh b/examples/aishell/transformer/infer.sh
deleted file mode 100644
index bcd4305..0000000
--- a/examples/aishell/transformer/infer.sh
+++ /dev/null
@@ -1,12 +0,0 @@
-
-
-python -m funasr.bin.inference \
---config-path="/mnt/workspace/FunASR/examples/aishell/paraformer/exp/baseline_paraformer_conformer_12e_6d_2048_256_zh_char_exp3" \
---config-name="config.yaml" \
-++init_param="/mnt/workspace/FunASR/examples/aishell/paraformer/exp/baseline_paraformer_conformer_12e_6d_2048_256_zh_char_exp3/model.pt.ep38" \
-++tokenizer_conf.token_list="/mnt/nfs/zhifu.gzf/data/AISHELL-1-feats/DATA/data/zh_token_list/char/tokens.txt" \
-++frontend_conf.cmvn_file="/mnt/nfs/zhifu.gzf/data/AISHELL-1-feats/DATA/data/train/am.mvn" \
-++input="/mnt/nfs/zhifu.gzf/data/AISHELL-1/data_aishell/wav/train/S0002/BAC009S0002W0122.wav" \
-++output_dir="./outputs/debug" \
-++device="cuda:0" \
-
diff --git a/examples/industrial_data_pretraining/bicif_paraformer/infer.sh b/examples/industrial_data_pretraining/bicif_paraformer/demo.sh
similarity index 100%
rename from examples/industrial_data_pretraining/bicif_paraformer/infer.sh
rename to examples/industrial_data_pretraining/bicif_paraformer/demo.sh
diff --git a/examples/industrial_data_pretraining/conformer/infer.sh b/examples/industrial_data_pretraining/conformer/demo.sh
similarity index 100%
rename from examples/industrial_data_pretraining/conformer/infer.sh
rename to examples/industrial_data_pretraining/conformer/demo.sh
diff --git a/examples/industrial_data_pretraining/contextual_paraformer/infer.sh b/examples/industrial_data_pretraining/contextual_paraformer/demo.sh
similarity index 100%
rename from examples/industrial_data_pretraining/contextual_paraformer/infer.sh
rename to examples/industrial_data_pretraining/contextual_paraformer/demo.sh
diff --git a/examples/industrial_data_pretraining/ct_transformer/infer.sh b/examples/industrial_data_pretraining/ct_transformer/demo.sh
similarity index 100%
rename from examples/industrial_data_pretraining/ct_transformer/infer.sh
rename to examples/industrial_data_pretraining/ct_transformer/demo.sh
diff --git a/examples/industrial_data_pretraining/ct_transformer_streaming/infer.sh b/examples/industrial_data_pretraining/ct_transformer_streaming/demo.sh
similarity index 100%
rename from examples/industrial_data_pretraining/ct_transformer_streaming/infer.sh
rename to examples/industrial_data_pretraining/ct_transformer_streaming/demo.sh
diff --git a/examples/industrial_data_pretraining/emotion2vec/infer.sh b/examples/industrial_data_pretraining/emotion2vec/infer.sh
deleted file mode 100644
index df990b9..0000000
--- a/examples/industrial_data_pretraining/emotion2vec/infer.sh
+++ /dev/null
@@ -1,12 +0,0 @@
-
-#model="damo/emotion2vec_base"
-model="iic/emotion2vec_base_finetuned"
-model_revision="v2.0.4"
-
-python funasr/bin/inference.py \
-+model=${model} \
-+model_revision=${model_revision} \
-+input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav" \
-+output_dir="./outputs/debug" \
-+extract_embedding=False \
-+device="cpu" \
diff --git a/examples/industrial_data_pretraining/fsmn_vad_streaming/infer.sh b/examples/industrial_data_pretraining/fsmn_vad_streaming/demo.sh
similarity index 100%
rename from examples/industrial_data_pretraining/fsmn_vad_streaming/infer.sh
rename to examples/industrial_data_pretraining/fsmn_vad_streaming/demo.sh
diff --git a/examples/industrial_data_pretraining/monotonic_aligner/infer.sh b/examples/industrial_data_pretraining/monotonic_aligner/demo.sh
similarity index 100%
rename from examples/industrial_data_pretraining/monotonic_aligner/infer.sh
rename to examples/industrial_data_pretraining/monotonic_aligner/demo.sh
diff --git a/examples/industrial_data_pretraining/paraformer-zh-spk/infer.sh b/examples/industrial_data_pretraining/paraformer-zh-spk/demo.sh
similarity index 100%
rename from examples/industrial_data_pretraining/paraformer-zh-spk/infer.sh
rename to examples/industrial_data_pretraining/paraformer-zh-spk/demo.sh
diff --git a/examples/industrial_data_pretraining/paraformer/demo.sh b/examples/industrial_data_pretraining/paraformer/demo.sh
deleted file mode 100644
index f9a03f9..0000000
--- a/examples/industrial_data_pretraining/paraformer/demo.sh
+++ /dev/null
@@ -1,14 +0,0 @@
-
-model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-model_revision="v2.0.4"
-
-python funasr/bin/inference.py \
-+model=${model} \
-+model_revision=${model_revision} \
-+input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav" \
-+output_dir="./outputs/debug" \
-+device="cpu" \
-
-
-
-
diff --git a/examples/industrial_data_pretraining/paraformer/finetune.sh b/examples/industrial_data_pretraining/paraformer/finetune.sh
index 266346c..21b29b6 100644
--- a/examples/industrial_data_pretraining/paraformer/finetune.sh
+++ b/examples/industrial_data_pretraining/paraformer/finetune.sh
@@ -1,9 +1,14 @@
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+# MIT License (https://opensource.org/licenses/MIT)
-## download model
-#local_path_root=../modelscope_models
-#mkdir -p ${local_path_root}
-#local_path=${local_path_root}/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
-#git clone https://www.modelscope.cn/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git ${local_path}
+# method1, finetune from model hub
+
+# which gpu to train or finetune
+export CUDA_VISIBLE_DEVICES="0,1"
+gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+
+# data dir, which contains: train.json, val.json
+data_dir="/Users/zhifu/funasr1.0/data/list"
## generate jsonl from wav.scp and text.txt
#python -m funasr.datasets.audio_datasets.scp2jsonl \
@@ -11,17 +16,29 @@
#++data_type_list='["source", "target"]' \
#++jsonl_file_out=/Users/zhifu/funasr1.0/test_local/audio_datasets.jsonl
+train_data="${data_dir}/train.jsonl"
+val_data="${data_dir}/val.jsonl"
-# torchrun \
-# --nnodes 1 \
-# --nproc_per_node 1 \
-python funasr/bin/train.py \
-+model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
-+model_revision="v2.0.4" \
-+train_data_set_list="/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len_10.jsonl" \
-+valid_data_set_list="/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len_10.jsonl" \
-++dataset_conf.batch_size=64 \
+
+# exp output dir
+output_dir="/Users/zhifu/exp"
+log_file="${output_dir}/log.txt"
+
+
+mkdir -p ${output_dir}
+echo "log_file: ${log_file}"
+
+torchrun \
+--nnodes 1 \
+--nproc_per_node ${gpu_num} \
+funasr/bin/train.py \
+++model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
+++model_revision="v2.0.4" \
+++train_data_set_list="${train_data}" \
+++valid_data_set_list="${val_data}" \
+++dataset_conf.batch_size=32 \
++dataset_conf.batch_type="example" \
-++train_conf.max_epoch=2 \
++dataset_conf.num_workers=4 \
-+output_dir="outputs/debug/ckpt/funasr2/exp2"
\ No newline at end of file
+++train_conf.max_epoch=20 \
+++optim_conf.lr=0.0002 \
+++output_dir="${output_dir}" &> ${log_file}
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/paraformer/finetune_from_local.sh b/examples/industrial_data_pretraining/paraformer/finetune_from_local.sh
new file mode 100644
index 0000000..5b4d991
--- /dev/null
+++ b/examples/industrial_data_pretraining/paraformer/finetune_from_local.sh
@@ -0,0 +1,61 @@
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+# MIT License (https://opensource.org/licenses/MIT)
+
+# method2, finetune from local model
+
+workspace=`pwd`
+
+# download model
+local_path_root=${workspace}/modelscope_models
+mkdir -p ${local_path_root}
+local_path=${local_path_root}/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
+git clone https://www.modelscope.cn/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git ${local_path}
+
+
+# which gpu to train or finetune
+export CUDA_VISIBLE_DEVICES="0,1"
+gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+
+# data dir, which contains: train.json, val.json
+data_dir="/Users/zhifu/funasr1.0/data/list"
+
+## generate jsonl from wav.scp and text.txt
+#python -m funasr.datasets.audio_datasets.scp2jsonl \
+#++scp_file_list='["/Users/zhifu/funasr1.0/test_local/wav.scp", "/Users/zhifu/funasr1.0/test_local/text.txt"]' \
+#++data_type_list='["source", "target"]' \
+#++jsonl_file_out=/Users/zhifu/funasr1.0/test_local/audio_datasets.jsonl
+
+train_data="${data_dir}/train.jsonl"
+val_data="${data_dir}/val.jsonl"
+
+tokens="${local_path}/tokens.json"
+cmvn_file="${local_path}/am.mvn"
+
+# exp output dir
+output_dir="/Users/zhifu/exp"
+log_file="${output_dir}/log.txt"
+
+config="config.yaml"
+
+init_param="${local_path}/model.pt"
+
+mkdir -p ${output_dir}
+echo "log_file: ${log_file}"
+
+torchrun \
+--nnodes 1 \
+--nproc_per_node ${gpu_num} \
+../../../funasr/bin/train.py \
+--config-path "${local_path}" \
+--config-name "${config}" \
+++train_data_set_list="${train_data}" \
+++valid_data_set_list="${val_data}" \
+++tokenizer_conf.token_list="${tokens}" \
+++frontend_conf.cmvn_file="${cmvn_file}" \
+++dataset_conf.batch_size=32 \
+++dataset_conf.batch_type="example" \
+++dataset_conf.num_workers=4 \
+++train_conf.max_epoch=20 \
+++optim_conf.lr=0.0002 \
+++init_param="${init_param}" \
+++output_dir="${output_dir}" &> ${log_file}
diff --git a/examples/industrial_data_pretraining/paraformer/infer.sh b/examples/industrial_data_pretraining/paraformer/infer.sh
new file mode 100644
index 0000000..a1975ea
--- /dev/null
+++ b/examples/industrial_data_pretraining/paraformer/infer.sh
@@ -0,0 +1,21 @@
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+# MIT License (https://opensource.org/licenses/MIT)
+
+# method1, inference from model hub
+
+# for more input type, please ref to readme.md
+input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
+
+output_dir="./outputs/debug"
+
+model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+model_revision="v2.0.4"
+
+device="cuda:0" # "cuda:0" for gpu0, "cuda:1" for gpu1, "cpu"
+
+python -m funasr.bin.inference \
+++model=${model} \
+++model_revision=${model_revision} \
+++input="${input}" \
+++output_dir="${output_dir}" \
+++device="${device}" \
diff --git a/examples/industrial_data_pretraining/paraformer/infer_after_finetune.sh b/examples/industrial_data_pretraining/paraformer/infer_after_finetune.sh
deleted file mode 100644
index 94797bf..0000000
--- a/examples/industrial_data_pretraining/paraformer/infer_after_finetune.sh
+++ /dev/null
@@ -1,12 +0,0 @@
-
-
-python funasr/bin/inference.py \
---config-path="/Users/zhifu/funasr_github/test_local/funasr_cli_egs" \
---config-name="config.yaml" \
-++init_param="/Users/zhifu/funasr_github/test_local/funasr_cli_egs/model.pt" \
-++tokenizer_conf.token_list="/Users/zhifu/funasr_github/test_local/funasr_cli_egs/tokens.txt" \
-++frontend_conf.cmvn_file="/Users/zhifu/funasr_github/test_local/funasr_cli_egs/am.mvn" \
-++input="data/wav.scp" \
-++output_dir="./outputs/debug" \
-++device="cuda" \
-
diff --git a/examples/industrial_data_pretraining/paraformer/infer_from_local.sh b/examples/industrial_data_pretraining/paraformer/infer_from_local.sh
new file mode 100644
index 0000000..06c9ca6
--- /dev/null
+++ b/examples/industrial_data_pretraining/paraformer/infer_from_local.sh
@@ -0,0 +1,39 @@
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+# MIT License (https://opensource.org/licenses/MIT)
+
+# method2, inference from local model
+
+# for more input type, please ref to readme.md
+input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
+
+output_dir="./outputs/debug"
+
+workspace=`pwd`
+
+# download model
+local_path_root=${workspace}/modelscope_models
+mkdir -p ${local_path_root}
+local_path=${local_path_root}/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
+git clone https://www.modelscope.cn/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git ${local_path}
+
+device="cuda:0" # "cuda:0" for gpu0, "cuda:1" for gpu1, "cpu"
+
+tokens="${local_path}/tokens.json"
+cmvn_file="${local_path}/am.mvn"
+
+config="config.yaml"
+init_param="${local_path}/model.pt"
+
+python -m funasr.bin.inference \
+--config-path "${local_path}" \
+--config-name "${config}" \
+++init_param="${init_param}" \
+++tokenizer_conf.token_list="${tokens}" \
+++frontend_conf.cmvn_file="${cmvn_file}" \
+++input="${input}" \
+++output_dir="${output_dir}" \
+++device="${device}" \
+
+
+
+
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/infer.sh b/examples/industrial_data_pretraining/paraformer_streaming/demo.sh
similarity index 100%
rename from examples/industrial_data_pretraining/paraformer_streaming/infer.sh
rename to examples/industrial_data_pretraining/paraformer_streaming/demo.sh
diff --git a/examples/industrial_data_pretraining/scama/infer.sh b/examples/industrial_data_pretraining/scama/demo.sh
similarity index 100%
rename from examples/industrial_data_pretraining/scama/infer.sh
rename to examples/industrial_data_pretraining/scama/demo.sh
diff --git a/examples/industrial_data_pretraining/seaco_paraformer/infer.sh b/examples/industrial_data_pretraining/seaco_paraformer/demo.sh
similarity index 100%
rename from examples/industrial_data_pretraining/seaco_paraformer/infer.sh
rename to examples/industrial_data_pretraining/seaco_paraformer/demo.sh
diff --git a/examples/industrial_data_pretraining/transducer/demo.py b/examples/industrial_data_pretraining/transducer/demo.py
new file mode 100644
index 0000000..ef12aac
--- /dev/null
+++ b/examples/industrial_data_pretraining/transducer/demo.py
@@ -0,0 +1,15 @@
+#!/usr/bin/env python3
+# -*- encoding: utf-8 -*-
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+# MIT License (https://opensource.org/licenses/MIT)
+
+from funasr import AutoModel
+
+# Transducer, BAT and RWKV_BAT models are just same to use, use the correct model_revision
+# https://modelscope.cn/models?name=transducer&page=1&tasks=auto-speech-recognition&type=audio
+model = AutoModel(model="iic/speech_bat_asr-zh-cn-16k-aishell1-vocab4234-pytorch",
+ model_revision="v2.0.2",
+ )
+
+res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
+print(res)
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/uniasr/infer.sh b/examples/industrial_data_pretraining/uniasr/demo.sh
similarity index 100%
rename from examples/industrial_data_pretraining/uniasr/infer.sh
rename to examples/industrial_data_pretraining/uniasr/demo.sh
diff --git a/funasr/bin/train.py b/funasr/bin/train.py
index 0661452..4538224 100644
--- a/funasr/bin/train.py
+++ b/funasr/bin/train.py
@@ -96,15 +96,18 @@
init_param = (init_param,)
logging.info("init_param is not None: %s", init_param)
for p in init_param:
- logging.info(f"Loading pretrained params from {p}")
- load_pretrained_model(
- model=model,
- path=p,
- ignore_init_mismatch=kwargs.get("ignore_init_mismatch", True),
- oss_bucket=kwargs.get("oss_bucket", None),
- scope_map=kwargs.get("scope_map", None),
- excludes=kwargs.get("excludes", None),
- )
+ if os.path.exists(p):
+ logging.info(f"Loading pretrained params from {p}")
+ load_pretrained_model(
+ model=model,
+ path=p,
+ ignore_init_mismatch=kwargs.get("ignore_init_mismatch", True),
+ oss_bucket=kwargs.get("oss_bucket", None),
+ scope_map=kwargs.get("scope_map", None),
+ excludes=kwargs.get("excludes", None),
+ )
+ else:
+ logging.info(f"Checkpoint does not exist, init randomly: {p}")
else:
initialize(model, kwargs.get("init", "kaiming_normal"))
diff --git a/funasr/models/bat/model.py b/funasr/models/bat/model.py
index 8e76b45..bdfcba6 100644
--- a/funasr/models/bat/model.py
+++ b/funasr/models/bat/model.py
@@ -13,6 +13,7 @@
from funasr.register import tables
from funasr.utils import postprocess_utils
from funasr.utils.datadir_writer import DatadirWriter
+from funasr.models.transducer.model import Transducer
from funasr.train_utils.device_funcs import force_gatherable
from funasr.models.transformer.scorers.ctc import CTCPrefixScorer
from funasr.losses.label_smoothing_loss import LabelSmoothingLoss
@@ -32,488 +33,5 @@
@tables.register("model_classes", "BAT") # TODO: BAT training
-class BAT(torch.nn.Module):
- def __init__(
- self,
- frontend: Optional[str] = None,
- frontend_conf: Optional[Dict] = None,
- specaug: Optional[str] = None,
- specaug_conf: Optional[Dict] = None,
- normalize: str = None,
- normalize_conf: Optional[Dict] = None,
- encoder: str = None,
- encoder_conf: Optional[Dict] = None,
- decoder: str = None,
- decoder_conf: Optional[Dict] = None,
- joint_network: str = None,
- joint_network_conf: Optional[Dict] = None,
- transducer_weight: float = 1.0,
- fastemit_lambda: float = 0.0,
- auxiliary_ctc_weight: float = 0.0,
- auxiliary_ctc_dropout_rate: float = 0.0,
- auxiliary_lm_loss_weight: float = 0.0,
- auxiliary_lm_loss_smoothing: float = 0.0,
- input_size: int = 80,
- vocab_size: int = -1,
- ignore_id: int = -1,
- blank_id: int = 0,
- sos: int = 1,
- eos: int = 2,
- lsm_weight: float = 0.0,
- length_normalized_loss: bool = False,
- # report_cer: bool = True,
- # report_wer: bool = True,
- # sym_space: str = "<space>",
- # sym_blank: str = "<blank>",
- # extract_feats_in_collect_stats: bool = True,
- share_embedding: bool = False,
- # preencoder: Optional[AbsPreEncoder] = None,
- # postencoder: Optional[AbsPostEncoder] = None,
- **kwargs,
- ):
-
- super().__init__()
-
- if specaug is not None:
- specaug_class = tables.specaug_classes.get(specaug)
- specaug = specaug_class(**specaug_conf)
- if normalize is not None:
- normalize_class = tables.normalize_classes.get(normalize)
- normalize = normalize_class(**normalize_conf)
- encoder_class = tables.encoder_classes.get(encoder)
- encoder = encoder_class(input_size=input_size, **encoder_conf)
- encoder_output_size = encoder.output_size()
-
- decoder_class = tables.decoder_classes.get(decoder)
- decoder = decoder_class(
- vocab_size=vocab_size,
- **decoder_conf,
- )
- decoder_output_size = decoder.output_size
-
- joint_network_class = tables.joint_network_classes.get(joint_network)
- joint_network = joint_network_class(
- vocab_size,
- encoder_output_size,
- decoder_output_size,
- **joint_network_conf,
- )
-
- self.criterion_transducer = None
- self.error_calculator = None
-
- self.use_auxiliary_ctc = auxiliary_ctc_weight > 0
- self.use_auxiliary_lm_loss = auxiliary_lm_loss_weight > 0
-
- if self.use_auxiliary_ctc:
- self.ctc_lin = torch.nn.Linear(encoder.output_size(), vocab_size)
- self.ctc_dropout_rate = auxiliary_ctc_dropout_rate
-
- if self.use_auxiliary_lm_loss:
- self.lm_lin = torch.nn.Linear(decoder.output_size, vocab_size)
- self.lm_loss_smoothing = auxiliary_lm_loss_smoothing
-
- self.transducer_weight = transducer_weight
- self.fastemit_lambda = fastemit_lambda
-
- self.auxiliary_ctc_weight = auxiliary_ctc_weight
- self.auxiliary_lm_loss_weight = auxiliary_lm_loss_weight
- self.blank_id = blank_id
- self.sos = sos if sos is not None else vocab_size - 1
- self.eos = eos if eos is not None else vocab_size - 1
- self.vocab_size = vocab_size
- self.ignore_id = ignore_id
- self.frontend = frontend
- self.specaug = specaug
- self.normalize = normalize
- self.encoder = encoder
- self.decoder = decoder
- self.joint_network = joint_network
-
- self.criterion_att = LabelSmoothingLoss(
- size=vocab_size,
- padding_idx=ignore_id,
- smoothing=lsm_weight,
- normalize_length=length_normalized_loss,
- )
-
- self.length_normalized_loss = length_normalized_loss
- self.beam_search = None
- self.ctc = None
- self.ctc_weight = 0.0
-
- def forward(
- self,
- speech: torch.Tensor,
- speech_lengths: torch.Tensor,
- text: torch.Tensor,
- text_lengths: torch.Tensor,
- **kwargs,
- ) -> Tuple[torch.Tensor, Dict[str, torch.Tensor], torch.Tensor]:
- """Encoder + Decoder + Calc loss
- Args:
- speech: (Batch, Length, ...)
- speech_lengths: (Batch, )
- text: (Batch, Length)
- text_lengths: (Batch,)
- """
- if len(text_lengths.size()) > 1:
- text_lengths = text_lengths[:, 0]
- if len(speech_lengths.size()) > 1:
- speech_lengths = speech_lengths[:, 0]
-
- batch_size = speech.shape[0]
- # 1. Encoder
- encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
- if hasattr(self.encoder, 'overlap_chunk_cls') and self.encoder.overlap_chunk_cls is not None:
- encoder_out, encoder_out_lens = self.encoder.overlap_chunk_cls.remove_chunk(encoder_out, encoder_out_lens,
- chunk_outs=None)
- # 2. Transducer-related I/O preparation
- decoder_in, target, t_len, u_len = get_transducer_task_io(
- text,
- encoder_out_lens,
- ignore_id=self.ignore_id,
- )
-
- # 3. Decoder
- self.decoder.set_device(encoder_out.device)
- decoder_out = self.decoder(decoder_in, u_len)
-
- # 4. Joint Network
- joint_out = self.joint_network(
- encoder_out.unsqueeze(2), decoder_out.unsqueeze(1)
- )
-
- # 5. Losses
- loss_trans, cer_trans, wer_trans = self._calc_transducer_loss(
- encoder_out,
- joint_out,
- target,
- t_len,
- u_len,
- )
-
- loss_ctc, loss_lm = 0.0, 0.0
-
- if self.use_auxiliary_ctc:
- loss_ctc = self._calc_ctc_loss(
- encoder_out,
- target,
- t_len,
- u_len,
- )
-
- if self.use_auxiliary_lm_loss:
- loss_lm = self._calc_lm_loss(decoder_out, target)
-
- loss = (
- self.transducer_weight * loss_trans
- + self.auxiliary_ctc_weight * loss_ctc
- + self.auxiliary_lm_loss_weight * loss_lm
- )
-
- stats = dict(
- loss=loss.detach(),
- loss_transducer=loss_trans.detach(),
- aux_ctc_loss=loss_ctc.detach() if loss_ctc > 0.0 else None,
- aux_lm_loss=loss_lm.detach() if loss_lm > 0.0 else None,
- cer_transducer=cer_trans,
- wer_transducer=wer_trans,
- )
-
- # force_gatherable: to-device and to-tensor if scalar for DataParallel
- loss, stats, weight = force_gatherable((loss, stats, batch_size), loss.device)
-
- return loss, stats, weight
-
- def encode(
- self, speech: torch.Tensor, speech_lengths: torch.Tensor, **kwargs,
- ) -> Tuple[torch.Tensor, torch.Tensor]:
- """Frontend + Encoder. Note that this method is used by asr_inference.py
- Args:
- speech: (Batch, Length, ...)
- speech_lengths: (Batch, )
- ind: int
- """
- with autocast(False):
-
- # Data augmentation
- if self.specaug is not None and self.training:
- speech, speech_lengths = self.specaug(speech, speech_lengths)
-
- # Normalization for feature: e.g. Global-CMVN, Utterance-CMVN
- if self.normalize is not None:
- speech, speech_lengths = self.normalize(speech, speech_lengths)
-
- # Forward encoder
- # feats: (Batch, Length, Dim)
- # -> encoder_out: (Batch, Length2, Dim2)
- encoder_out, encoder_out_lens, _ = self.encoder(speech, speech_lengths)
- intermediate_outs = None
- if isinstance(encoder_out, tuple):
- intermediate_outs = encoder_out[1]
- encoder_out = encoder_out[0]
-
- if intermediate_outs is not None:
- return (encoder_out, intermediate_outs), encoder_out_lens
-
- return encoder_out, encoder_out_lens
-
- def _calc_transducer_loss(
- self,
- encoder_out: torch.Tensor,
- joint_out: torch.Tensor,
- target: torch.Tensor,
- t_len: torch.Tensor,
- u_len: torch.Tensor,
- ) -> Tuple[torch.Tensor, Optional[float], Optional[float]]:
- """Compute Transducer loss.
-
- Args:
- encoder_out: Encoder output sequences. (B, T, D_enc)
- joint_out: Joint Network output sequences (B, T, U, D_joint)
- target: Target label ID sequences. (B, L)
- t_len: Encoder output sequences lengths. (B,)
- u_len: Target label ID sequences lengths. (B,)
-
- Return:
- loss_transducer: Transducer loss value.
- cer_transducer: Character error rate for Transducer.
- wer_transducer: Word Error Rate for Transducer.
-
- """
- if self.criterion_transducer is None:
- try:
- from warp_rnnt import rnnt_loss as RNNTLoss
- self.criterion_transducer = RNNTLoss
-
- except ImportError:
- logging.error(
- "warp-rnnt was not installed."
- "Please consult the installation documentation."
- )
- exit(1)
-
- log_probs = torch.log_softmax(joint_out, dim=-1)
-
- loss_transducer = self.criterion_transducer(
- log_probs,
- target,
- t_len,
- u_len,
- reduction="mean",
- blank=self.blank_id,
- fastemit_lambda=self.fastemit_lambda,
- gather=True,
- )
-
- if not self.training and (self.report_cer or self.report_wer):
- if self.error_calculator is None:
- from funasr.metrics import ErrorCalculatorTransducer as ErrorCalculator
-
- self.error_calculator = ErrorCalculator(
- self.decoder,
- self.joint_network,
- self.token_list,
- self.sym_space,
- self.sym_blank,
- report_cer=self.report_cer,
- report_wer=self.report_wer,
- )
-
- cer_transducer, wer_transducer = self.error_calculator(encoder_out, target, t_len)
-
- return loss_transducer, cer_transducer, wer_transducer
-
- return loss_transducer, None, None
-
- def _calc_ctc_loss(
- self,
- encoder_out: torch.Tensor,
- target: torch.Tensor,
- t_len: torch.Tensor,
- u_len: torch.Tensor,
- ) -> torch.Tensor:
- """Compute CTC loss.
-
- Args:
- encoder_out: Encoder output sequences. (B, T, D_enc)
- target: Target label ID sequences. (B, L)
- t_len: Encoder output sequences lengths. (B,)
- u_len: Target label ID sequences lengths. (B,)
-
- Return:
- loss_ctc: CTC loss value.
-
- """
- ctc_in = self.ctc_lin(
- torch.nn.functional.dropout(encoder_out, p=self.ctc_dropout_rate)
- )
- ctc_in = torch.log_softmax(ctc_in.transpose(0, 1), dim=-1)
-
- target_mask = target != 0
- ctc_target = target[target_mask].cpu()
-
- with torch.backends.cudnn.flags(deterministic=True):
- loss_ctc = torch.nn.functional.ctc_loss(
- ctc_in,
- ctc_target,
- t_len,
- u_len,
- zero_infinity=True,
- reduction="sum",
- )
- loss_ctc /= target.size(0)
-
- return loss_ctc
-
- def _calc_lm_loss(
- self,
- decoder_out: torch.Tensor,
- target: torch.Tensor,
- ) -> torch.Tensor:
- """Compute LM loss.
-
- Args:
- decoder_out: Decoder output sequences. (B, U, D_dec)
- target: Target label ID sequences. (B, L)
-
- Return:
- loss_lm: LM loss value.
-
- """
- lm_loss_in = self.lm_lin(decoder_out[:, :-1, :]).view(-1, self.vocab_size)
- lm_target = target.view(-1).type(torch.int64)
-
- with torch.no_grad():
- true_dist = lm_loss_in.clone()
- true_dist.fill_(self.lm_loss_smoothing / (self.vocab_size - 1))
-
- # Ignore blank ID (0)
- ignore = lm_target == 0
- lm_target = lm_target.masked_fill(ignore, 0)
-
- true_dist.scatter_(1, lm_target.unsqueeze(1), (1 - self.lm_loss_smoothing))
-
- loss_lm = torch.nn.functional.kl_div(
- torch.log_softmax(lm_loss_in, dim=1),
- true_dist,
- reduction="none",
- )
- loss_lm = loss_lm.masked_fill(ignore.unsqueeze(1), 0).sum() / decoder_out.size(
- 0
- )
-
- return loss_lm
-
- def init_beam_search(self,
- **kwargs,
- ):
-
- # 1. Build ASR model
- scorers = {}
-
- if self.ctc != None:
- ctc = CTCPrefixScorer(ctc=self.ctc, eos=self.eos)
- scorers.update(
- ctc=ctc
- )
- token_list = kwargs.get("token_list")
- scorers.update(
- length_bonus=LengthBonus(len(token_list)),
- )
-
- # 3. Build ngram model
- # ngram is not supported now
- ngram = None
- scorers["ngram"] = ngram
-
- beam_search = BeamSearchTransducer(
- self.decoder,
- self.joint_network,
- kwargs.get("beam_size", 2),
- nbest=1,
- )
- # beam_search.to(device=kwargs.get("device", "cpu"), dtype=getattr(torch, kwargs.get("dtype", "float32"))).eval()
- # for scorer in scorers.values():
- # if isinstance(scorer, torch.nn.Module):
- # scorer.to(device=kwargs.get("device", "cpu"), dtype=getattr(torch, kwargs.get("dtype", "float32"))).eval()
- self.beam_search = beam_search
-
- def inference(self,
- data_in: list,
- data_lengths: list=None,
- key: list=None,
- tokenizer=None,
- **kwargs,
- ):
-
- if kwargs.get("batch_size", 1) > 1:
- raise NotImplementedError("batch decoding is not implemented")
-
- # init beamsearch
- is_use_ctc = kwargs.get("decoding_ctc_weight", 0.0) > 0.00001 and self.ctc != None
- is_use_lm = kwargs.get("lm_weight", 0.0) > 0.00001 and kwargs.get("lm_file", None) is not None
- # if self.beam_search is None and (is_use_lm or is_use_ctc):
- logging.info("enable beam_search")
- self.init_beam_search(**kwargs)
- self.nbest = kwargs.get("nbest", 1)
-
- meta_data = {}
- # extract fbank feats
- time1 = time.perf_counter()
- audio_sample_list = load_audio_text_image_video(data_in, fs=self.frontend.fs, audio_fs=kwargs.get("fs", 16000))
- time2 = time.perf_counter()
- meta_data["load_data"] = f"{time2 - time1:0.3f}"
- speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"), frontend=self.frontend)
- time3 = time.perf_counter()
- meta_data["extract_feat"] = f"{time3 - time2:0.3f}"
- meta_data["batch_data_time"] = speech_lengths.sum().item() * self.frontend.frame_shift * self.frontend.lfr_n / 1000
-
- speech = speech.to(device=kwargs["device"])
- speech_lengths = speech_lengths.to(device=kwargs["device"])
-
- # Encoder
- encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
- if isinstance(encoder_out, tuple):
- encoder_out = encoder_out[0]
-
- # c. Passed the encoder result and the beam search
- nbest_hyps = self.beam_search(encoder_out[0], is_final=True)
- nbest_hyps = nbest_hyps[: self.nbest]
-
- results = []
- b, n, d = encoder_out.size()
- for i in range(b):
-
- for nbest_idx, hyp in enumerate(nbest_hyps):
- ibest_writer = None
- if kwargs.get("output_dir") is not None:
- if not hasattr(self, "writer"):
- self.writer = DatadirWriter(kwargs.get("output_dir"))
- ibest_writer = self.writer[f"{nbest_idx + 1}best_recog"]
- # remove sos/eos and get results
- last_pos = -1
- if isinstance(hyp.yseq, list):
- token_int = hyp.yseq#[1:last_pos]
- else:
- token_int = hyp.yseq#[1:last_pos].tolist()
-
- # remove blank symbol id, which is assumed to be 0
- token_int = list(filter(lambda x: x != self.eos and x != self.sos and x != self.blank_id, token_int))
-
- # Change integer-ids to tokens
- token = tokenizer.ids2tokens(token_int)
- text = tokenizer.tokens2text(token)
-
- text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
- result_i = {"key": key[i], "token": token, "text": text, "text_postprocessed": text_postprocessed}
- results.append(result_i)
-
- if ibest_writer is not None:
- ibest_writer["token"][key[i]] = " ".join(token)
- ibest_writer["text"][key[i]] = text
- ibest_writer["text_postprocessed"][key[i]] = text_postprocessed
-
- return results, meta_data
-
+class BAT(Transducer):
+ pass
\ No newline at end of file
diff --git a/funasr/train_utils/load_pretrained_model.py b/funasr/train_utils/load_pretrained_model.py
index 5ba9bb7..8493bf5 100644
--- a/funasr/train_utils/load_pretrained_model.py
+++ b/funasr/train_utils/load_pretrained_model.py
@@ -96,8 +96,7 @@
obj = model
dst_state = obj.state_dict()
- # import pdb;
- # pdb.set_trace()
+
print(f"ckpt: {path}")
if oss_bucket is None:
src_state = torch.load(path, map_location=map_location)
@@ -106,7 +105,9 @@
src_state = torch.load(buffer, map_location=map_location)
if "state_dict" in src_state:
src_state = src_state["state_dict"]
-
+
+ src_state = src_state["model"] if "model" in src_state else src_state
+
for k in dst_state.keys():
if not k.startswith("module.") and "module." + k in src_state.keys():
k_ddp = "module." + k
@@ -115,7 +116,7 @@
if k_ddp in src_state:
dst_state[k] = src_state[k_ddp]
else:
- print(f"Miss key in ckpt: model: {k}, ckpt: {k_ddp}")
+ print(f"Warning, miss key in ckpt: {k}, mapped: {k_ddp}")
flag = obj.load_state_dict(dst_state, strict=True)
# print(flag)
diff --git a/funasr/train_utils/trainer.py b/funasr/train_utils/trainer.py
index 6a59f91..d175fbe 100644
--- a/funasr/train_utils/trainer.py
+++ b/funasr/train_utils/trainer.py
@@ -181,7 +181,7 @@
time2 = time.perf_counter()
time_escaped = (time2 - time1)/3600.0
- print(f"\nrank: {self.local_rank}, time_escaped_epoch: {time_escaped:.3f} hours, estimated to finish {self.max_epoch} epoch: {(self.max_epoch-epoch)*time_escaped:.3f}\n")
+ print(f"\nrank: {self.local_rank}, time_escaped_epoch: {time_escaped:.3f} hours, estimated to finish {self.max_epoch} epoch: {(self.max_epoch-epoch)*time_escaped:.3f} hours\n")
if self.rank == 0:
average_checkpoints(self.output_dir, self.avg_nbest_model)
@@ -293,7 +293,7 @@
f"{time_now}, "
f"rank: {self.local_rank}, "
f"epoch: {epoch}/{self.max_epoch}, "
- f"step: {batch_idx+1}/{len(self.dataloader_train)}, total: {self.batch_total}, "
+ f"step: {batch_idx+1}/{len(self.dataloader_train)}, total step: {self.batch_total}, "
f"(loss: {loss.detach().cpu().item():.3f}), "
f"(lr: {lr:.3e}), "
f"{[(k, round(v.cpu().item(), 3)) for k, v in stats.items()]}, "
diff --git a/funasr/version.txt b/funasr/version.txt
index b0f3d96..7ee7020 100644
--- a/funasr/version.txt
+++ b/funasr/version.txt
@@ -1 +1 @@
-1.0.8
+1.0.10
--
Gitblit v1.9.1