| | |
|---|
| | | |
|---|
| | | 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), ...] |
|---|
| | |
|---|
| | | 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: |
|---|
| | |
|---|
| | | ibest_writer["score"][key] = str(hyp.score) |
|---|
| | | |
|---|
| | | if text is not None: |
|---|
| | | text_postprocessed = postprocess_utils.sentence_postprocess(token) |
|---|
| | | text_postprocessed, _ = postprocess_utils.sentence_postprocess(token) |
|---|
| | | item = {'key': key, 'value': text_postprocessed} |
|---|
| | | asr_result_list.append(item) |
|---|
| | | finish_count += 1 |
|---|
| | |
|---|
| | | return asr_result_list |
|---|
| | | |
|---|
| | | return _forward |
|---|
| | | |
|---|
| | | def set_parameters(language: str = None, |
|---|
| | | sample_rate: Union[int, Dict[Any, int]] = None): |
|---|
| | | if language is not None: |
|---|
| | | global global_asr_language |
|---|
| | | global_asr_language = language |
|---|
| | | if sample_rate is not None: |
|---|
| | | global global_sample_rate |
|---|
| | | global_sample_rate = sample_rate |
|---|
| | | |
|---|
| | | |
|---|
| | | def get_parser(): |
|---|
| | | parser = config_argparse.ArgumentParser( |
|---|
