| | |
|---|
| | | self.nbest = kwargs.get("nbest", 1) |
|---|
| | | |
|---|
| | | meta_data = {} |
|---|
| | | if isinstance(data_in, torch.Tensor): # fbank |
|---|
| | | if isinstance(data_in, torch.Tensor) and kwargs.get("data_type", "sound") == "fbank": # fbank |
|---|
| | | speech, speech_lengths = data_in, data_lengths |
|---|
| | | if len(speech.shape) < 3: |
|---|
| | | speech = speech[None, :, :] |
|---|
| | |
|---|
| | | b, n, d = decoder_out.size() |
|---|
| | | if isinstance(key[0], (list, tuple)): |
|---|
| | | key = key[0] |
|---|
| | | if len(key) < b: |
|---|
| | | key = key*b |
|---|
| | | for i in range(b): |
|---|
| | | x = encoder_out[i, :encoder_out_lens[i], :] |
|---|
| | | am_scores = decoder_out[i, :pre_token_length[i], :] |
|---|
| | |
|---|
| | | if tokenizer is not None: |
|---|
| | | # Change integer-ids to tokens |
|---|
| | | token = tokenizer.ids2tokens(token_int) |
|---|
| | | text = tokenizer.tokens2text(token) |
|---|
| | | |
|---|
| | | text_postprocessed, _ = postprocess_utils.sentence_postprocess(token) |
|---|
| | | text_postprocessed = tokenizer.tokens2text(token) |
|---|
| | | if not hasattr(tokenizer, "bpemodel"): |
|---|
| | | text_postprocessed, _ = postprocess_utils.sentence_postprocess(token) |
|---|
| | | |
|---|
| | | result_i = {"key": key[i], "text": text_postprocessed} |
|---|
| | | |
|---|
