| | |
|---|
| | | results = speech2text(**batch) |
|---|
| | | if len(results) < 1: |
|---|
| | | hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[]) |
|---|
| | | results = [[" ", ["<space>"], [2], hyp, 10, 6]] * nbest |
|---|
| | | results = [[" ", ["sil"], [2], hyp, 10, 6]] * nbest |
|---|
| | | time_end = time.time() |
|---|
| | | forward_time = time_end - time_beg |
|---|
| | | lfr_factor = results[0][-1] |
|---|
| | |
|---|
| | | 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 |
|---|
| | |
|---|
| | | logging.info("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))) |
|---|
| | | return asr_result_list |
|---|
| | | |
|---|
| | | |
|---|
| | | 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(): |
|---|
