add english paraformer model

egs_modelscope/asr/paraformer/speech_paraformer_asr-en-16k-vocab4199-pytorch/README.md

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

egs_modelscope/asr/paraformer/speech_paraformer_asr-en-16k-vocab4199-pytorch/demo.py

@@ -0,0 +1,11 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model='damo/damo/speech_paraformer_asr-en-16k-vocab4199-pytorch',
+    model_revision="v1.0.1",
+)
+audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav'
+rec_result = inference_pipeline(audio_in=audio_in)
+print(rec_result)

egs_modelscope/asr/paraformer/speech_paraformer_asr-en-16k-vocab4199-pytorch/finetune.py

@@ -0,0 +1,36 @@
+import os
+
+from modelscope.metainfo import Trainers
+from modelscope.trainers import build_trainer
+
+from funasr.datasets.ms_dataset import MsDataset
+from funasr.utils.modelscope_param import modelscope_args
+
+
+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_path)
+    kwargs = dict(
+        model=params.model,
+        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 = modelscope_args(model="damo/speech_paraformer_asr-en-16k-vocab4199-pytorch", data_path="./data")
+    params.output_dir = "./checkpoint"              # m模型保存路径
+    params.data_path = "./example_data/"            # 数据路径
+    params.dataset_type = "small"                   # 小数据量设置small，若数据量大于1000小时，请使用large
+    params.batch_bins = 2000                       # batch size，如果dataset_type="small"，batch_bins单位为fbank特征帧数，如果dataset_type="large"，batch_bins单位为毫秒，
+    params.max_epoch = 50                           # 最大训练轮数
+    params.lr = 0.00005                             # 设置学习率
+    
+    modelscope_finetune(params)

egs_modelscope/asr/paraformer/speech_paraformer_asr-en-16k-vocab4199-pytorch/infer.py

@@ -0,0 +1 @@
+../../TEMPLATE/infer.py

egs_modelscope/asr/paraformer/speech_paraformer_asr-en-16k-vocab4199-pytorch/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_asr-en-16k-vocab4199-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/paraformer/speech_paraformer_asr-en-16k-vocab4199-pytorch/utils

@@ -0,0 +1 @@
+../../../../egs/aishell/transformer/utils