| | |
| | | |
| | | 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), ...] |
| | |
| | | |
| | | # remove blank symbol id, which is assumed to be 0 |
| | | token_int = list(filter(lambda x: x != 0 and x != 2, token_int)) |
| | | if len(token_int) == 0: |
| | | continue |
| | | |
| | | # Change integer-ids to tokens |
| | | token = self.converter.ids2tokens(token_int) |
| | |
| | | ibest_writer["token"][key] = " ".join(token) |
| | | ibest_writer["token_int"][key] = " ".join(map(str, token_int)) |
| | | ibest_writer["vad"][key] = "{}".format(vadsegments) |
| | | ibest_writer["text"][key] = text_postprocessed |
| | | ibest_writer["text"][key] = " ".join(word_lists) |
| | | ibest_writer["text_with_punc"][key] = text_postprocessed_punc |
| | | if time_stamp_postprocessed is not None: |
| | | ibest_writer["time_stamp"][key] = "{}".format(time_stamp_postprocessed) |