| | |
|---|
| | | from funasr.utils.types import str2triple_str |
|---|
| | | from funasr.utils.types import str_or_none |
|---|
| | | |
|---|
| | | from modelscope.utils.logger import get_logger |
|---|
| | | logger = get_logger() |
|---|
| | | |
|---|
| | | class Speech2Diarization: |
|---|
| | | """Speech2Diarlization class |
|---|
| | | |
|---|
| | |
|---|
| | | 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, |
|---|
| | |
|---|
| | | 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"] |
|---|
| | | logger.info(data_path_and_name_and_type) |
|---|
| | | data_path_and_name_and_type = [raw_inputs[0], "speech", "bytes"] |
|---|
| | | loader = EENDOLADiarTask.build_streaming_iterator( |
|---|
| | | data_path_and_name_and_type, |
|---|
| | | dtype=dtype, |
|---|
| | |
|---|
| | | output_writer = open("{}/result.txt".format(output_path), "w") |
|---|
| | | result_list = [] |
|---|
| | | for keys, batch in loader: |
|---|
| | | logger.info("keys: {}".format(keys)) |
|---|
| | | logger.info("batch: {}".format(batch)) |
|---|
| | | assert isinstance(batch, dict), type(batch) |
|---|
| | | assert all(isinstance(s, str) for s in keys), keys |
|---|
| | | _bs = len(next(iter(batch.values()))) |
|---|
