egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
@@ -16,7 +16,7 @@ if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument('--model', type=str, default="speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch") 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") parser.add_argument('--output_dir', type=str, default="./results/") parser.add_argument('--batch_size', type=int, default=64) egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh
@@ -64,8 +64,8 @@ if [ $stage -le 2 ] && [ $stop_stage -ge 2 ];then echo "Computing WER ..." python utils/proce_text.py ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc python utils/proce_text.py ${data_dir}/text ${data_dir}/text.proc python utils/compute_wer.py ${data_dir}/text.proc ${output_dir}/1best_recog/text.proc ${output_dir}/1best_recog/text.cer python utils/proce_text.py ${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 @@ -75,7 +75,7 @@ ./utils/textnorm_zh.py \ --has_key --to_upper \ ${data_dir}/text \ ${data_dir}/ref.txt ${output_dir}/1best_recog/ref.txt echo "$0 --> Normalizing HYP text ..." ./utils/textnorm_zh.py \ @@ -87,7 +87,7 @@ echo "$0 --> computing WER/CER and alignment ..." ./utils/error_rate_zh \ --tokenizer char \ --ref ${data_dir}/ref.txt \ --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 ${output_dir}/1best_recog/rec_non_empty.txt egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/README.md
@@ -6,8 +6,9 @@ - Modify finetune training related parameters in `finetune.py` - <strong>output_dir:</strong> # result dir - <strong>data_dir:</strong> # the dataset dir needs to include files: train/wav.scp, train/text; validation/wav.scp, validation/text. - <strong>batch_bins:</strong> # batch size - <strong>data_dir:</strong> # the dataset dir needs to include files: `train/wav.scp`, `train/text`; `validation/wav.scp`, `validation/text` - <strong>dataset_type:</strong> # for dataset larger than 1000 hours, set as `large`, otherwise set as `small` - <strong>batch_bins:</strong> # batch size. For dataset_type is `small`, `batch_bins` indicates the feature frames. For dataset_type is `large`, `batch_bins` indicates the duration in ms - <strong>max_epoch:</strong> # number of training epoch - <strong>lr:</strong> # learning rate @@ -20,11 +21,38 @@ Or you can use the finetuned model for inference directly. - Setting parameters in `infer.py` - <strong>data_dir:</strong> # the dataset dir - Setting parameters in `infer.sh` - <strong>model:</strong> # model name on ModelScope - <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed - <strong>output_dir:</strong> # result dir - <strong>batch_size:</strong> # batchsize of inference - <strong>gpu_inference:</strong> # whether to perform gpu decoding, set false for cpu decoding - <strong>gpuid_list:</strong> # set gpus, e.g., gpuid_list="0,1" - <strong>njob:</strong> # the number of jobs for CPU decoding, if `gpu_inference`=false, use CPU decoding, please set `njob` - Then you can run the pipeline to infer with: ```python python infer.py sh infer.sh ``` - Results The decoding results can be found in `$output_dir/1best_recog/text.cer`, which includes recognition results 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` - <strong>modelscope_model_name: </strong> # model name on ModelScope - <strong>output_dir:</strong> # result dir - <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb` - <strong>batch_size:</strong> # batchsize of inference - 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/decoding_results/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set. egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py
@@ -1,101 +1,25 @@ 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, batch_size, ngpu, model): output_dir_job = os.path.join(output_dir, "output.{}".format(idx)) if ngpu > 0: use_gpu = 1 gpu_id = int(idx) - 1 else: use_gpu = 0 gpu_id = -1 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=model, output_dir=output_dir_job, batch_size=batch_size, ngpu=use_gpu, model=args.model, 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"] batch_size = params["batch_size"] output_dir = params["output_dir"] model = params["model"] 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) if ngpu > 0: nj = ngpu elif ngpu == 0: nj = 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), batch_size, ngpu, model)) 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") compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer")) inference_pipeline(audio_in=args.audio_in) if __name__ == "__main__": params = {} params["model"] = "damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1" params["data_dir"] = "./data/test" params["output_dir"] = "./results" params["ngpu"] = 1 # if ngpu > 0, will use gpu decoding params["njob"] = 1 # if ngpu = 0, will use cpu decoding params["batch_size"] = 64 modelscope_infer(params) parser = argparse.ArgumentParser() parser.add_argument('--model', type=str, default="damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1") parser.add_argument('--audio_in', type=str, default="./data/test") parser.add_argument('--output_dir', type=str, default="./results/") 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-8k-common-vocab8358-tensorflow1/infer.sh
New file @@ -0,0 +1,70 @@ #!/usr/bin/env bash set -e set -u set -o pipefail stage=1 stop_stage=2 model="damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1" 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=4 # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob if ${gpu_inference}; then nj=$(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//,/ }) 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 ..." python utils/proce_text.py ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc python utils/proce_text.py ${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 egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/utils
New file @@ -0,0 +1 @@ ../../../../egs/aishell/transformer/utils
