| | |
|---|
| | | from funasr.utils.types import str2triple_str |
|---|
| | | from funasr.utils.types import str_or_none |
|---|
| | | |
|---|
| | | |
|---|
| | | class Speech2Diarization: |
|---|
| | | """Speech2Diarlization class |
|---|
| | | |
|---|
| | |
|---|
| | | Currently, the tags of espnet_model_zoo are supported. |
|---|
| | | |
|---|
| | | Returns: |
|---|
| | | Speech2Xvector: Speech2Xvector instance. |
|---|
| | | Speech2Diarization: Speech2Diarization instance. |
|---|
| | | |
|---|
| | | """ |
|---|
| | | if model_tag is not None: |
|---|
| | |
|---|
| | | output_dir: Optional[str] = None, |
|---|
| | | batch_size: int = 1, |
|---|
| | | dtype: str = "float32", |
|---|
| | | ngpu: int = 0, |
|---|
| | | ngpu: int = 1, |
|---|
| | | num_workers: int = 0, |
|---|
| | | log_level: Union[int, str] = "INFO", |
|---|
| | | key_file: Optional[str] = None, |
|---|
| | |
|---|
| | | diar_model_file=diar_model_file, |
|---|
| | | device=device, |
|---|
| | | dtype=dtype, |
|---|
| | | streaming=streaming, |
|---|
| | | ) |
|---|
| | | logging.info("speech2diarization_kwargs: {}".format(speech2diar_kwargs)) |
|---|
| | | speech2diar = Speech2Diarization.from_pretrained( |
|---|
| | |
|---|
| | | if data_path_and_name_and_type is None and raw_inputs is not None: |
|---|
| | | if isinstance(raw_inputs, torch.Tensor): |
|---|
| | | raw_inputs = raw_inputs.numpy() |
|---|
| | | data_path_and_name_and_type = [raw_inputs, "speech", "waveform"] |
|---|
| | | data_path_and_name_and_type = [raw_inputs[0], "speech", "bytes"] |
|---|
| | | loader = EENDOLADiarTask.build_streaming_iterator( |
|---|
| | | data_path_and_name_and_type, |
|---|
| | | dtype=dtype, |
|---|
