From e0401c12d8813036bbd7813383450a15b946d3c3 Mon Sep 17 00:00:00 2001 From: R1ckShi <2698127294@qq.com> Date: Tue, 31 Jan 2023 15:30:12 +0800 Subject: [PATCH 1/2] egs for paraformer tiny --- .../README.md | 30 +++++++ .../data/test/wav.scp | 3 + .../infer.py | 88 +++++++++++++++++++ 3 files changed, 121 insertions(+) create mode 100644 egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/README.md create mode 100644 egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/data/test/wav.scp create mode 100644 egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/infer.py diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/README.md b/egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/README.md new file mode 100644 index 000000000..1587d3d5d --- /dev/null +++ b/egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/README.md @@ -0,0 +1,30 @@ +# 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. + - batch_bins: # batch size + - 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 + - output_dir: # result dir + +- Then you can run the pipeline to infer with: +```python + python infer.py +``` diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/data/test/wav.scp b/egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/data/test/wav.scp new file mode 100644 index 000000000..1e194c429 --- /dev/null +++ b/egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/data/test/wav.scp @@ -0,0 +1,3 @@ +001 /Users/shixian/Downloads/0001_ACRD0001.wav +002 /Users/shixian/Downloads/0001_ACRD0002.wav +013 /Users/shixian/Downloads/0001_ACRD0013.wav diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/infer.py b/egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/infer.py new file mode 100644 index 000000000..d1fbca22d --- /dev/null +++ b/egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/infer.py @@ -0,0 +1,88 @@ +import os +import shutil +from multiprocessing import Pool + +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( + task=Tasks.auto_speech_recognition, + model="damo/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch", + output_dir=output_dir_job, + batch_size=64 + ) + 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") + compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer")) + + +if __name__ == "__main__": + params = {} + params["data_dir"] = "./data/test" + params["output_dir"] = "./results" + params["ngpu"] = 1 + params["njob"] = 1 + modelscope_infer(params) From 9f4bb0a0ee2e0c4e48fa06156ece67603b3098d7 Mon Sep 17 00:00:00 2001 From: R1ckShi <2698127294@qq.com> Date: Tue, 31 Jan 2023 15:32:15 +0800 Subject: [PATCH 2/2] egs for paraformer-tiny --- .../data/test/wav.scp | 3 --- 1 file changed, 3 deletions(-) delete mode 100644 egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/data/test/wav.scp diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/data/test/wav.scp b/egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/data/test/wav.scp deleted file mode 100644 index 1e194c429..000000000 --- a/egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/data/test/wav.scp +++ /dev/null @@ -1,3 +0,0 @@ -001 /Users/shixian/Downloads/0001_ACRD0001.wav -002 /Users/shixian/Downloads/0001_ACRD0002.wav -013 /Users/shixian/Downloads/0001_ACRD0013.wav