Merge remote-tracking branch 'origin/main'

.github/workflows/main.yml

@@ -23,7 +23,7 @@ jobs:
           pre-build-command: "pip install sphinx-markdown-tables nbsphinx jinja2 recommonmark sphinx_rtd_theme myst-parser"
 
       - name: deploy copy
-        if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/dev_wjm' || github.ref == 'refs/heads/dev_lyh'
+        if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/dev_wjm' || github.ref == 'refs/heads/dev_lyh' || github.ref == 'refs/heads/dev_lhn'
         run: |
           mkdir public
           touch public/.nojekyll
@@ -35,7 +35,7 @@ jobs:
           cp -r docs/m2met2/_build/html/* public/m2met2/
 
       - name: deploy github.io pages
-        if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/dev_wjm' || github.ref == 'refs/heads/dev_lyh'
+        if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/dev_wjm' || github.ref == 'refs/heads/dev_lyh' || github.ref == 'refs/heads/dev_lhn'
         uses: peaceiris/actions-gh-pages@v2.3.1
         env:
           GITHUB_TOKEN: ${{ secrets.ACCESS_TOKEN }}

egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/README.md

@@ -0,0 +1 @@
+../TEMPLATE/README.md

egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/README_zh.md

@@ -0,0 +1 @@
+../TEMPLATE/README_zh.md

egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/demo.py

@@ -0,0 +1,18 @@
+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_en.wav'
+    output_dir = "./results"
+    inference_pipeline = pipeline(
+        task=Tasks.auto_speech_recognition,
+        model='damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020',
+        model_revision='v1.0.0',
+        vad_model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',
+        punc_model='damo/punc_ct-transformer_cn-en-common-vocab471067-large',
+        punc_model_revision='v1.0.0',
+        output_dir=output_dir,
+    )
+    rec_result = inference_pipeline(audio_in=audio_in, batch_size_token=5000, batch_size_token_threshold_s=40, max_single_segment_time=6000)
+    print(rec_result)
+

egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/infer.py

@@ -0,0 +1,27 @@
+import os
+import shutil
+import argparse
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+def modelscope_infer(args):
+    os.environ['CUDA_VISIBLE_DEVICES'] = str(args.gpuid)
+    inference_pipeline = pipeline(
+        task=Tasks.auto_speech_recognition,
+        model=args.model,
+        output_dir=args.output_dir,
+        param_dict={"decoding_model": args.decoding_mode, "hotword": args.hotword_txt}
+    )
+    inference_pipeline(audio_in=args.audio_in, batch_size_token=args.batch_size_token)
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--model', type=str, default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
+    parser.add_argument('--audio_in', type=str, default="./data/test/wav.scp")
+    parser.add_argument('--output_dir', type=str, default="./results/")
+    parser.add_argument('--decoding_mode', type=str, default="normal")
+    parser.add_argument('--hotword_txt', type=str, default=None)
+    parser.add_argument('--batch_size_token', type=int, default=5000)
+    parser.add_argument('--gpuid', type=str, default="0")
+    args = parser.parse_args()
+    modelscope_infer(args)

egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/infer.sh

@@ -0,0 +1,103 @@
+#!/usr/bin/env bash
+
+set -e
+set -u
+set -o pipefail
+
+stage=1
+stop_stage=2
+model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+data_dir="./data/test"
+output_dir="./results"
+batch_size=64
+gpu_inference=true    # whether to perform gpu decoding
+gpuid_list="0,1"    # set gpus, e.g., gpuid_list="0,1"
+njob=64    # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob
+checkpoint_dir=
+checkpoint_name="valid.cer_ctc.ave.pb"
+
+. utils/parse_options.sh || exit 1;
+
+if ${gpu_inference} == "true"; then
+    nj=$(echo $gpuid_list | awk -F "," '{print NF}')
+else
+    nj=$njob
+    batch_size=1
+    gpuid_list=""
+    for JOB in $(seq ${nj}); do
+        gpuid_list=$gpuid_list"-1,"
+    done
+fi
+
+mkdir -p $output_dir/split
+split_scps=""
+for JOB in $(seq ${nj}); do
+    split_scps="$split_scps $output_dir/split/wav.$JOB.scp"
+done
+perl utils/split_scp.pl ${data_dir}/wav.scp ${split_scps}
+
+if [ -n "${checkpoint_dir}" ]; then
+  python utils/prepare_checkpoint.py ${model} ${checkpoint_dir} ${checkpoint_name}
+  model=${checkpoint_dir}/${model}
+fi
+
+if [ $stage -le 1 ] && [ $stop_stage -ge 1 ];then
+    echo "Decoding ..."
+    gpuid_list_array=(${gpuid_list//,/ })
+    for JOB in $(seq ${nj}); do
+        {
+        id=$((JOB-1))
+        gpuid=${gpuid_list_array[$id]}
+        mkdir -p ${output_dir}/output.$JOB
+        python infer.py \
+            --model ${model} \
+            --audio_in ${output_dir}/split/wav.$JOB.scp \
+            --output_dir ${output_dir}/output.$JOB \
+            --batch_size ${batch_size} \
+            --gpuid ${gpuid}
+        }&
+    done
+    wait
+
+    mkdir -p ${output_dir}/1best_recog
+    for f in token score text; do
+        if [ -f "${output_dir}/output.1/1best_recog/${f}" ]; then
+          for i in $(seq "${nj}"); do
+              cat "${output_dir}/output.${i}/1best_recog/${f}"
+          done | sort -k1 >"${output_dir}/1best_recog/${f}"
+        fi
+    done
+fi
+
+if [ $stage -le 2 ] && [ $stop_stage -ge 2 ];then
+    echo "Computing WER ..."
+    cp ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc
+    cp ${data_dir}/text ${output_dir}/1best_recog/text.ref
+    python utils/compute_wer.py ${output_dir}/1best_recog/text.ref ${output_dir}/1best_recog/text.proc ${output_dir}/1best_recog/text.cer
+    tail -n 3 ${output_dir}/1best_recog/text.cer
+fi
+
+if [ $stage -le 3 ] && [ $stop_stage -ge 3 ];then
+    echo "SpeechIO TIOBE textnorm"
+    echo "$0 --> Normalizing REF text ..."
+    ./utils/textnorm_zh.py \
+        --has_key --to_upper \
+        ${data_dir}/text \
+        ${output_dir}/1best_recog/ref.txt
+
+    echo "$0 --> Normalizing HYP text ..."
+    ./utils/textnorm_zh.py \
+        --has_key --to_upper \
+        ${output_dir}/1best_recog/text.proc \
+        ${output_dir}/1best_recog/rec.txt
+    grep -v $'\t$' ${output_dir}/1best_recog/rec.txt > ${output_dir}/1best_recog/rec_non_empty.txt
+
+    echo "$0 --> computing WER/CER and alignment ..."
+    ./utils/error_rate_zh \
+        --tokenizer char \
+        --ref ${output_dir}/1best_recog/ref.txt \
+        --hyp ${output_dir}/1best_recog/rec_non_empty.txt \
+        ${output_dir}/1best_recog/DETAILS.txt | tee ${output_dir}/1best_recog/RESULTS.txt
+    rm -rf ${output_dir}/1best_recog/rec.txt ${output_dir}/1best_recog/rec_non_empty.txt
+fi
+

egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/utils

@@ -0,0 +1 @@
+../../asr/TEMPLATE/utils

funasr/datasets/large_datasets/dataset.py

@@ -108,7 +108,7 @@ class AudioDataset(IterableDataset):
                     ark_reader = ReadHelper('ark:{}'.format(data_file))
                     reader_list.append(ark_reader)
                 elif data_type == "text" or data_type == "sound" or data_type == 'text_hotword':
-                    text_reader = open(data_file, "r")
+                    text_reader = open(data_file, "r", encoding="utf-8")
                     reader_list.append(text_reader)
                 elif data_type == "none":
                     continue
@@ -205,7 +205,7 @@ def Dataset(data_list_file,
     # pre_prob = conf.get("pre_prob", 0)  # unused yet
     if pre_hwfile is not None:
         pre_hwlist = []
-        with open(pre_hwfile, 'r') as fin:
+        with open(pre_hwfile, 'r', encoding="utf-8") as fin:
             for line in fin.readlines():
                 pre_hwlist.append(line.strip())
     else: