Merge pull request #574 from alibaba-damo-academy/dev_lhn3

hnluo

2023-05-31 70410873c04e1a1916f20f5498a8e50c9e3ed657

Merge pull request #574 from alibaba-damo-academy/dev_lhn3

update

 egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/README.md

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

 egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/demo.py

@@ -1,39 +1,12 @@
import os
import logging
import torch
import soundfile

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.utils.logger import get_logger

logger = get_logger(log_level=logging.CRITICAL)
logger.setLevel(logging.CRITICAL)

os.environ["MODELSCOPE_CACHE"] = "./"
inference_pipeline = pipeline(
    task=Tasks.auto_speech_recognition,
    model='damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online',
    model_revision='v1.0.4'
    model_revision='v1.0.6',
    mode="paraformer_fake_streaming"
)

model_dir = os.path.join(os.environ["MODELSCOPE_CACHE"], "damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online")
speech, sample_rate = soundfile.read(os.path.join(model_dir, "example/asr_example.wav"))
speech_length = speech.shape[0]

sample_offset = 0
chunk_size = [8, 8, 4] #[5, 10, 5] 600ms, [8, 8, 4] 480ms
stride_size =  chunk_size[1] * 960
param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size}
final_result = ""

for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)):
    if sample_offset + stride_size >= speech_length - 1:
        stride_size = speech_length - sample_offset
        param_dict["is_final"] = True
    rec_result = inference_pipeline(audio_in=speech[sample_offset: sample_offset + stride_size],
                                    param_dict=param_dict)
    if len(rec_result) != 0:
        final_result += rec_result['text']
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
rec_result = inference_pipeline(audio_in=audio_in)
        print(rec_result)
print(final_result.strip())

 egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/demo_online.py

New file
@@ -0,0 +1,40 @@
import os
import logging
import torch
import soundfile

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.utils.logger import get_logger

logger = get_logger(log_level=logging.CRITICAL)
logger.setLevel(logging.CRITICAL)

os.environ["MODELSCOPE_CACHE"] = "./"
inference_pipeline = pipeline(
    task=Tasks.auto_speech_recognition,
    model='damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online',
    model_revision='v1.0.6',
    mode="paraformer_streaming"
)

model_dir = os.path.join(os.environ["MODELSCOPE_CACHE"], "damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online")
speech, sample_rate = soundfile.read(os.path.join(model_dir, "example/asr_example.wav"))
speech_length = speech.shape[0]

sample_offset = 0
chunk_size = [8, 8, 4] #[5, 10, 5] 600ms, [8, 8, 4] 480ms
stride_size =  chunk_size[1] * 960
param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size}
final_result = ""

for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)):
    if sample_offset + stride_size >= speech_length - 1:
        stride_size = speech_length - sample_offset
        param_dict["is_final"] = True
    rec_result = inference_pipeline(audio_in=speech[sample_offset: sample_offset + stride_size],
                                    param_dict=param_dict)
    if len(rec_result) != 0:
        final_result += rec_result['text']
        print(rec_result)
print(final_result)

 egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/finetune.py

New file
@@ -0,0 +1,37 @@
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,
        model_revision='v1.0.6',
        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_nat-zh-cn-16k-common-vocab8404-online", 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 = 1000                       # 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 = 20                           # 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_nat-zh-cn-16k-common-vocab8404-online/infer.py

New file
@@ -0,0 +1,32 @@
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,
        batch_size=args.batch_size,
        model_revision='v1.0.6',
        mode="paraformer_fake_streaming",
        param_dict={"decoding_model": args.decoding_mode, "hotword": args.hotword_txt}
    )
    inference_pipeline(audio_in=args.audio_in)

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('--model_revision', type=str, default=None)
    parser.add_argument('--mode', type=str, default=None)
    parser.add_argument('--hotword_txt', type=str, default=None)
    parser.add_argument('--batch_size', type=int, default=64)
    parser.add_argument('--gpuid', type=str, default="0")
    args = parser.parse_args()
    modelscope_infer(args)

 egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/infer.sh

New file
@@ -0,0 +1,104 @@
#!/usr/bin/env bash

set -e
set -u
set -o pipefail

stage=1
stop_stage=2
model="damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online"
data_dir="./data/test"
output_dir="./results"
batch_size=32
gpu_inference=true    # whether to perform gpu decoding
gpuid_list="0,1"    # set gpus, e.g., gpuid_list="0,1"
njob=32    # 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}
            --mode "paraformer_fake_streaming"
        }&
    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_nat-zh-cn-16k-common-vocab8404-online/utils

New file
@@ -0,0 +1 @@
../../TEMPLATE/utils/