| | |
|---|
| | | |
|---|
| | | 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), ...] |
|---|
| | |
|---|
| | | **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: |
|---|
| | |
|---|
| | | output_dir_v2: Optional[str] = None, |
|---|
| | | fs: dict = None, |
|---|
| | | param_dict: dict = None, |
|---|
| | | **kwargs, |
|---|
| | | ): |
|---|
| | | # 3. Build data-iterator |
|---|
| | | if data_path_and_name_and_type is None and raw_inputs is not None: |
|---|
