python/FunASR-XL.git

parent: 2ce5a1cb | 补丁 | 提交 | show whitespace

yufan-aslp

2023-04-25 cfe22850e2a62071fca0fbdc15bb6e95ca555490

update mfcc infer.sh

2个文件已修改

3个文件已添加

1个文件已删除

	egs_modelscope/asr/TEMPLATE/README.md	16 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史
	egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md	53 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史
	egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md	1 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史
	egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer.py	111 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史
	egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer.sh	70 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史
	egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/utils	1 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史

 egs_modelscope/asr/TEMPLATE/README.md

@@ -58,6 +58,22 @@
#### [RNN-T-online model]()
Undo

#### [MFCCA Model](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary)
For more model detailes, please refer to [docs](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary)
```python
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

inference_pipeline = pipeline(
    task=Tasks.auto_speech_recognition,
    model='NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950',
    model_revision='v3.0.0'
)

rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
print(rec_result)
```

#### API-reference
##### Define pipeline
- `task`: `Tasks.auto_speech_recognition`

 egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md

File was deleted

 egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md

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

 egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer.py

@@ -1,102 +1,27 @@
import os
import shutil
from multiprocessing import Pool

import argparse
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

from funasr.utils.compute_wer import compute_wer

def modelscope_infer_core(output_dir, split_dir, njob, idx):
    output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
    gpu_id = (int(idx) - 1) // njob
    if "CUDA_VISIBLE_DEVICES" in os.environ.keys():
        gpu_list = os.environ['CUDA_VISIBLE_DEVICES'].split(",")
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
    else:
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
    inference_pipline = pipeline(
def modelscope_infer(args):
    os.environ['CUDA_VISIBLE_DEVICES'] = str(args.gpuid)
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model='NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950',
        model_revision='v3.0.0',
        output_dir=output_dir_job,
        batch_size=1,
        model=args.model,
        model_revision=args.model_revision,
        output_dir=args.output_dir,
        batch_size=args.batch_size,
    )
    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
    inference_pipline(audio_in=audio_in)


def modelscope_infer(params):
    # prepare for multi-GPU decoding
    ngpu = params["ngpu"]
    njob = params["njob"]
    output_dir = params["output_dir"]
    if os.path.exists(output_dir):
        shutil.rmtree(output_dir)
    os.mkdir(output_dir)
    split_dir = os.path.join(output_dir, "split")
    os.mkdir(split_dir)
    nj = ngpu * njob
    wav_scp_file = os.path.join(params["data_dir"], "wav.scp")
    with open(wav_scp_file) as f:
        lines = f.readlines()
        num_lines = len(lines)
        num_job_lines = num_lines // nj
    start = 0
    for i in range(nj):
        end = start + num_job_lines
        file = os.path.join(split_dir, "wav.{}.scp".format(str(i + 1)))
        with open(file, "w") as f:
            if i == nj - 1:
                f.writelines(lines[start:])
            else:
                f.writelines(lines[start:end])
        start = end
    p = Pool(nj)
    for i in range(nj):
        p.apply_async(modelscope_infer_core,
                      args=(output_dir, split_dir, njob, str(i + 1)))
    p.close()
    p.join()

    # combine decoding results
    best_recog_path = os.path.join(output_dir, "1best_recog")
    os.mkdir(best_recog_path)
    files = ["text", "token", "score"]
    for file in files:
        with open(os.path.join(best_recog_path, file), "w") as f:
            for i in range(nj):
                job_file = os.path.join(output_dir, "output.{}/1best_recog".format(str(i + 1)), file)
                with open(job_file) as f_job:
                    lines = f_job.readlines()
                f.writelines(lines)

    # If text exists, compute CER
    text_in = os.path.join(params["data_dir"], "text")
    if os.path.exists(text_in):
        text_proc_file = os.path.join(best_recog_path, "token")
        text_proc_file2 = os.path.join(best_recog_path, "token_nosep")
        with open(text_proc_file, 'r') as hyp_reader:
                with open(text_proc_file2, 'w') as hyp_writer:
                    for line in hyp_reader:
                        new_context = line.strip().replace("src","").replace("  "," ").replace("  "," ").strip()
                        hyp_writer.write(new_context+'\n')
        text_in2 = os.path.join(best_recog_path, "ref_text_nosep")
        with open(text_in, 'r') as ref_reader:
            with open(text_in2, 'w') as ref_writer:
                for line in ref_reader:
                    new_context = line.strip().replace("src","").replace("  "," ").replace("  "," ").strip()
                    ref_writer.write(new_context+'\n')


        compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.sp.cer"))
        compute_wer(text_in2, text_proc_file2, os.path.join(best_recog_path, "text.nosp.cer"))

    inference_pipeline(audio_in=args.audio_in)

if __name__ == "__main__":
    params = {}
    params["data_dir"] = "./example_data/validation"
    params["output_dir"] = "./output_dir"
    params["ngpu"] = 1
    params["njob"] = 1
    modelscope_infer(params)
    parser = argparse.ArgumentParser()
    parser.add_argument('--model', type=str, default="NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950")
    parser.add_argument('--model_revision', type=str, default="v3.0.0")
    parser.add_argument('--audio_in', type=str, default="./data/test/wav.scp")
    parser.add_argument('--output_dir', type=str, default="./results/")
    parser.add_argument('--batch_size', type=int, default=1)
    parser.add_argument('--gpuid', type=str, default="0")
    args = parser.parse_args()
    modelscope_infer(args)

 egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer.sh

New file
@@ -0,0 +1,70 @@
#!/usr/bin/env bash

set -e
set -u
set -o pipefail

stage=1
stop_stage=3
model="NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950"
data_dir="./data/test"
output_dir="./results_pl_gpu"
batch_size=1
gpu_inference=true    # whether to perform gpu decoding
gpuid_list="3,4"    # set gpus, e.g., gpuid_list="0,1"
njob=4    # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob

. 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 [ $stage -le 1 ] && [ $stop_stage -ge 1 ];then
    echo "Decoding ..."
    gpuid_list_array=(${gpuid_list//,/ })
    ./utils/run.pl JOB=1:${nj} ${output_dir}/log/infer.JOB.log \
    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_list_array[JOB-1]}

    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/token ${output_dir}/1best_recog/text.proc
    cp ${data_dir}/text ${output_dir}/1best_recog/text.ref
    sed -e 's/src//g' ${output_dir}/1best_recog/text.proc | sed -e 's/ \+/ /g' > ${output_dir}/1best_recog/text_nosp.proc
    sed -e 's/src//g' ${output_dir}/1best_recog/text.ref | sed -e 's/ \+/ /g' > ${output_dir}/1best_recog/text_nosp.ref

    python utils/compute_wer.py ${output_dir}/1best_recog/text.ref ${output_dir}/1best_recog/text.proc ${output_dir}/1best_recog/text.sp.cer
    tail -n 3 ${output_dir}/1best_recog/text.sp.cer
    python utils/compute_wer.py ${output_dir}/1best_recog/text_nosp.ref ${output_dir}/1best_recog/text_nosp.proc ${output_dir}/1best_recog/text.nosp.cer
    tail -n 3 ${output_dir}/1best_recog/text.nosp.cer
fi


 egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/utils

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

			@@ -58,6 +58,22 @@
			#### [RNN-T-online model]()
			Undo

			#### [MFCCA Model](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary)
			For more model detailes, please refer to [docs](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary)
			```python
			from modelscope.pipelines import pipeline
			from modelscope.utils.constant import Tasks

			inference_pipeline = pipeline(
			task=Tasks.auto_speech_recognition,
			model='NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950',
			model_revision='v3.0.0'
			)

			rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
			print(rec_result)
			```

			#### API-reference
			##### Define pipeline
			- `task`: `Tasks.auto_speech_recognition`

			@@ -1,102 +1,27 @@
			import os
			import shutil
			from multiprocessing import Pool

			import argparse
			from modelscope.pipelines import pipeline
			from modelscope.utils.constant import Tasks

			from funasr.utils.compute_wer import compute_wer

			def modelscope_infer_core(output_dir, split_dir, njob, idx):
			output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
			gpu_id = (int(idx) - 1) // njob
			if "CUDA_VISIBLE_DEVICES" in os.environ.keys():
			gpu_list = os.environ['CUDA_VISIBLE_DEVICES'].split(",")
			os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
			else:
			os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
			inference_pipline = pipeline(
			def modelscope_infer(args):
			os.environ['CUDA_VISIBLE_DEVICES'] = str(args.gpuid)
			inference_pipeline = pipeline(
			task=Tasks.auto_speech_recognition,
			model='NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950',
			model_revision='v3.0.0',
			output_dir=output_dir_job,
			batch_size=1,
			model=args.model,
			model_revision=args.model_revision,
			output_dir=args.output_dir,
			batch_size=args.batch_size,
			)
			audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
			inference_pipline(audio_in=audio_in)


			def modelscope_infer(params):
			# prepare for multi-GPU decoding
			ngpu = params["ngpu"]
			njob = params["njob"]
			output_dir = params["output_dir"]
			if os.path.exists(output_dir):
			shutil.rmtree(output_dir)
			os.mkdir(output_dir)
			split_dir = os.path.join(output_dir, "split")
			os.mkdir(split_dir)
			nj = ngpu * njob
			wav_scp_file = os.path.join(params["data_dir"], "wav.scp")
			with open(wav_scp_file) as f:
			lines = f.readlines()
			num_lines = len(lines)
			num_job_lines = num_lines // nj
			start = 0
			for i in range(nj):
			end = start + num_job_lines
			file = os.path.join(split_dir, "wav.{}.scp".format(str(i + 1)))
			with open(file, "w") as f:
			if i == nj - 1:
			f.writelines(lines[start:])
			else:
			f.writelines(lines[start:end])
			start = end
			p = Pool(nj)
			for i in range(nj):
			p.apply_async(modelscope_infer_core,
			args=(output_dir, split_dir, njob, str(i + 1)))
			p.close()
			p.join()

			# combine decoding results
			best_recog_path = os.path.join(output_dir, "1best_recog")
			os.mkdir(best_recog_path)
			files = ["text", "token", "score"]
			for file in files:
			with open(os.path.join(best_recog_path, file), "w") as f:
			for i in range(nj):
			job_file = os.path.join(output_dir, "output.{}/1best_recog".format(str(i + 1)), file)
			with open(job_file) as f_job:
			lines = f_job.readlines()
			f.writelines(lines)

			# If text exists, compute CER
			text_in = os.path.join(params["data_dir"], "text")
			if os.path.exists(text_in):
			text_proc_file = os.path.join(best_recog_path, "token")
			text_proc_file2 = os.path.join(best_recog_path, "token_nosep")
			with open(text_proc_file, 'r') as hyp_reader:
			with open(text_proc_file2, 'w') as hyp_writer:
			for line in hyp_reader:
			new_context = line.strip().replace("src","").replace(" "," ").replace(" "," ").strip()
			hyp_writer.write(new_context+'\n')
			text_in2 = os.path.join(best_recog_path, "ref_text_nosep")
			with open(text_in, 'r') as ref_reader:
			with open(text_in2, 'w') as ref_writer:
			for line in ref_reader:
			new_context = line.strip().replace("src","").replace(" "," ").replace(" "," ").strip()
			ref_writer.write(new_context+'\n')


			compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.sp.cer"))
			compute_wer(text_in2, text_proc_file2, os.path.join(best_recog_path, "text.nosp.cer"))

			inference_pipeline(audio_in=args.audio_in)

			if __name__ == "__main__":
			params = {}
			params["data_dir"] = "./example_data/validation"
			params["output_dir"] = "./output_dir"
			params["ngpu"] = 1
			params["njob"] = 1
			modelscope_infer(params)
			parser = argparse.ArgumentParser()
			parser.add_argument('--model', type=str, default="NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950")
			parser.add_argument('--model_revision', type=str, default="v3.0.0")
			parser.add_argument('--audio_in', type=str, default="./data/test/wav.scp")
			parser.add_argument('--output_dir', type=str, default="./results/")
			parser.add_argument('--batch_size', type=int, default=1)
			parser.add_argument('--gpuid', type=str, default="0")
			args = parser.parse_args()
			modelscope_infer(args)

New file
			@@ -0,0 +1,70 @@
			#!/usr/bin/env bash

			set -e
			set -u
			set -o pipefail

			stage=1
			stop_stage=3
			model="NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950"
			data_dir="./data/test"
			output_dir="./results_pl_gpu"
			batch_size=1
			gpu_inference=true # whether to perform gpu decoding
			gpuid_list="3,4" # set gpus, e.g., gpuid_list="0,1"
			njob=4 # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob

			. 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 [ $stage -le 1 ] && [ $stop_stage -ge 1 ];then
			echo "Decoding ..."
			gpuid_list_array=(${gpuid_list//,/ })
			./utils/run.pl JOB=1:${nj} ${output_dir}/log/infer.JOB.log \
			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_list_array[JOB-1]}

			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/token ${output_dir}/1best_recog/text.proc
			cp ${data_dir}/text ${output_dir}/1best_recog/text.ref
			sed -e 's/src//g' ${output_dir}/1best_recog/text.proc \| sed -e 's/ \+/ /g' > ${output_dir}/1best_recog/text_nosp.proc
			sed -e 's/src//g' ${output_dir}/1best_recog/text.ref \| sed -e 's/ \+/ /g' > ${output_dir}/1best_recog/text_nosp.ref

			python utils/compute_wer.py ${output_dir}/1best_recog/text.ref ${output_dir}/1best_recog/text.proc ${output_dir}/1best_recog/text.sp.cer
			tail -n 3 ${output_dir}/1best_recog/text.sp.cer
			python utils/compute_wer.py ${output_dir}/1best_recog/text_nosp.ref ${output_dir}/1best_recog/text_nosp.proc ${output_dir}/1best_recog/text.nosp.cer
			tail -n 3 ${output_dir}/1best_recog/text.nosp.cer
			fi

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