| | |
|---|
| | | |
|---|
| | | 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), ...] |
|---|
| | |
|---|
| | | raise NotImplementedError("Word LM is not implemented") |
|---|
| | | if ngpu > 1: |
|---|
| | | raise NotImplementedError("only single GPU decoding is supported") |
|---|
| | | |
|---|
| | | |
|---|
| | | for handler in logging.root.handlers[:]: |
|---|
| | | logging.root.removeHandler(handler) |
|---|
| | | |
|---|
| | | logging.basicConfig( |
|---|
| | | level=log_level, |
|---|
| | | format="%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s", |
|---|
| | |
|---|
| | | 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 |
|---|
