| | |
|---|
| | | from funasr.utils import asr_utils, wav_utils, postprocess_utils |
|---|
| | | import pdb |
|---|
| | | |
|---|
| | | header_colors = '\033[95m' |
|---|
| | | end_colors = '\033[0m' |
|---|
| | | |
|---|
| | | global_asr_language: str = 'zh-cn' |
|---|
| | | global_sample_rate: Union[int, Dict[Any, int]] = { |
|---|
| | |
|---|
| | | |
|---|
| | | Examples: |
|---|
| | | >>> import soundfile |
|---|
| | | >>> speech2text = Speech2Text("asr_config.yml", "asr.pth") |
|---|
| | | >>> speech2text = Speech2Text("asr_config.yml", "asr.pb") |
|---|
| | | >>> audio, rate = soundfile.read("speech.wav") |
|---|
| | | >>> speech2text(audio) |
|---|
| | | [(text, token, token_int, hypothesis object), ...] |
|---|
| | |
|---|
| | | # Input as audio signal |
|---|
| | | if isinstance(speech, np.ndarray): |
|---|
| | | speech = torch.tensor(speech) |
|---|
| | | |
|---|
| | | |
|---|
| | | if(speech.dim()==3): |
|---|
| | | speech = torch.squeeze(speech, 2) |
|---|
| | | #speech = speech.unsqueeze(0).to(getattr(torch, self.dtype)) |
|---|
| | | speech = speech.to(getattr(torch, self.dtype)) |
|---|
| | | # lenghts: (1,) |
|---|
| | |
|---|
| | | **kwargs, |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | | ncpu = kwargs.get("ncpu", 1) |
|---|
| | | torch.set_num_threads(ncpu) |
|---|
| | | if batch_size > 1: |
|---|
| | | raise NotImplementedError("batch decoding is not implemented") |
|---|
| | | if word_lm_train_config is not None: |
|---|
| | |
|---|
| | | data_path_and_name_and_type, |
|---|
| | | dtype=dtype, |
|---|
| | | batch_size=batch_size, |
|---|
| | | fs=fs, |
|---|
| | | mc=True, |
|---|
| | | key_file=key_file, |
|---|
| | | num_workers=num_workers, |
|---|
| | | preprocess_fn=ASRTask.build_preprocess_fn(speech2text.asr_train_args, False), |
|---|
