From 20c35cdbc7ab0962629c9d88fd0ca07ad3968050 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 22 二月 2024 12:07:30 +0800
Subject: [PATCH] Dev gzf (#1379)
---
.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/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 +++++++
README_zh.md | 2
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
32 files changed, 233 insertions(+), 41 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/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/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()]}, "
--
Gitblit v1.9.1