diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md index a064302a2..b7e76cb29 100644 --- a/egs_modelscope/asr/TEMPLATE/README.md +++ b/egs_modelscope/asr/TEMPLATE/README.md @@ -58,6 +58,22 @@ Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/ #### [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` diff --git a/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md b/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md deleted file mode 100644 index 16aeada4b..000000000 --- a/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md +++ /dev/null @@ -1,53 +0,0 @@ -# ModelScope Model - -## How to finetune and infer using a pretrained Paraformer-large Model - -### Finetune - -- Modify finetune training related parameters in `finetune.py` - - output_dir: # result dir - - data_dir: # the dataset dir needs to include files: `train/wav.scp`, `train/text`; `validation/wav.scp`, `validation/text` - - dataset_type: # for dataset larger than 1000 hours, set as `large`, otherwise set as `small` - - batch_bins: # batch size. For dataset_type is `small`, `batch_bins` indicates the feature frames. For dataset_type is `large`, `batch_bins` indicates the duration in ms - - max_epoch: # number of training epoch - - lr: # learning rate - -- Then you can run the pipeline to finetune with: -```python - python finetune.py -``` - -### Inference - -Or you can use the finetuned model for inference directly. - -- Setting parameters in `infer.py` - - data_dir: # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed - - output_dir: # result dir - - ngpu: # the number of GPUs for decoding - - njob: # the number of jobs for each GPU - -- Then you can run the pipeline to infer with: -```python - python infer.py -``` - -- Results - -The decoding results can be found in `$output_dir/1best_recog/text.sp.cer` and `$output_dir/1best_recog/text.nosp.cer`, which includes recognition results with or without separating character (src) of each sample and the CER metric of the whole test set. - -### Inference using local finetuned model - -- Modify inference related parameters in `infer_after_finetune.py` - - output_dir: # result dir - - data_dir: # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed - - decoding_model_name: # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb` - -- Then you can run the pipeline to finetune with: -```python - python infer_after_finetune.py -``` - -- Results - -The decoding results can be found in `$output_dir/1best_recog/text.sp.cer` and `$output_dir/1best_recog/text.nosp.cer`, which includes recognition results with or without separating character (src) of each sample and the CER metric of the whole test set. diff --git a/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md b/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md new file mode 120000 index 000000000..bb55ab52e --- /dev/null +++ b/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/README.md @@ -0,0 +1 @@ +../../TEMPLATE/README.md \ No newline at end of file diff --git a/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer.py b/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer.py index 8abadd719..12ec2ac8c 100755 --- a/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer.py +++ b/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) diff --git a/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer.sh b/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer.sh new file mode 100755 index 000000000..51a4968bc --- /dev/null +++ b/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer.sh @@ -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 + diff --git a/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/utils b/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/utils new file mode 120000 index 000000000..2ac163ff4 --- /dev/null +++ b/egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/utils @@ -0,0 +1 @@ +../../../../egs/aishell/transformer/utils \ No newline at end of file