| | |
|---|
| | | import os |
|---|
| | | import logging |
|---|
| | | import torch |
|---|
| | | import soundfile |
|---|
| | | |
|---|
| | | import shutil |
|---|
| | | import argparse |
|---|
| | | 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) |
|---|
| | | 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', |
|---|
| | | update_model=False, |
|---|
| | | mode="paraformer_fake_streaming", |
|---|
| | | param_dict={"decoding_model": args.decoding_mode, "hotword": args.hotword_txt} |
|---|
| | | ) |
|---|
| | | inference_pipeline(audio_in=args.audio_in) |
|---|
| | | |
|---|
| | | os.environ["MODELSCOPE_CACHE"] = "./" |
|---|
| | | inference_pipeline = pipeline( |
|---|
| | | task=Tasks.auto_speech_recognition, |
|---|
| | | model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online', |
|---|
| | | model_revision='v1.0.4' |
|---|
| | | ) |
|---|
| | | |
|---|
| | | model_dir = os.path.join(os.environ["MODELSCOPE_CACHE"], "damo/speech_paraformer-large_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 = [5, 10, 5] #[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 += " ".join(rec_result['text']) + " " |
|---|
| | | print(rec_result) |
|---|
| | | print(final_result) |
|---|
| | | 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) |
|---|
