| | |
|---|
| | | |
|---|
| | | 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), ...] |
|---|
| | |
|---|
| | | ibest_writer["rtf"][key] = rtf_cur |
|---|
| | | |
|---|
| | | if text is not None: |
|---|
| | | text_postprocessed, _ = postprocess_utils.sentence_postprocess(token) |
|---|
| | | text_postprocessed, word_lists = postprocess_utils.sentence_postprocess(token) |
|---|
| | | item = {'key': key, 'value': text_postprocessed} |
|---|
| | | asr_result_list.append(item) |
|---|
| | | finish_count += 1 |
|---|
| | | # asr_utils.print_progress(finish_count / file_count) |
|---|
| | | if writer is not None: |
|---|
| | | ibest_writer["text"][key] = text_postprocessed |
|---|
| | | ibest_writer["text"][key] = " ".join(word_lists) |
|---|
| | | |
|---|
| | | logging.info("decoding, utt: {}, predictions: {}".format(key, text)) |
|---|
| | | rtf_avg = "decoding, feature length total: {}, forward_time total: {:.4f}, rtf avg: {:.4f}".format(length_total, forward_time_total, 100 * forward_time_total / (length_total * lfr_factor)) |
|---|
