| | |
|---|
| | | from funasr.utils import asr_utils, wav_utils, postprocess_utils |
|---|
| | | from funasr.models.frontend.wav_frontend import WavFrontend |
|---|
| | | from funasr.models.e2e_asr_paraformer import BiCifParaformer, ContextualParaformer |
|---|
| | | from funasr.models.e2e_asr_contextual_paraformer import NeatContextualParaformer |
|---|
| | | from funasr.export.models.e2e_asr_paraformer import Paraformer as Paraformer_export |
|---|
| | | from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard |
|---|
| | | from funasr.bin.tp_inference import SpeechText2Timestamp |
|---|
| | |
|---|
| | | pre_token_length = pre_token_length.round().long() |
|---|
| | | if torch.max(pre_token_length) < 1: |
|---|
| | | return [] |
|---|
| | | if not isinstance(self.asr_model, ContextualParaformer): |
|---|
| | | if not isinstance(self.asr_model, ContextualParaformer) and not isinstance(self.asr_model, NeatContextualParaformer): |
|---|
| | | if self.hotword_list: |
|---|
| | | logging.warning("Hotword is given but asr model is not a ContextualParaformer.") |
|---|
| | | decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds, pre_token_length) |
|---|
| | |
|---|
| | | **kwargs, |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | | |
|---|
| | | ncpu = kwargs.get("ncpu", 1) |
|---|
| | | torch.set_num_threads(ncpu) |
|---|
| | | |
|---|
| | | if word_lm_train_config is not None: |
|---|
| | | raise NotImplementedError("Word LM is not implemented") |
|---|
| | | if ngpu > 1: |
|---|
| | |
|---|
| | | export_mode = param_dict.get("export_mode", False) |
|---|
| | | else: |
|---|
| | | hotword_list_or_file = None |
|---|
| | | |
|---|
| | | |
|---|
| | | if kwargs.get("device", None) == "cpu": |
|---|
| | | ngpu = 0 |
|---|
| | | if ngpu >= 1 and torch.cuda.is_available(): |
|---|
| | | device = "cuda" |
|---|
| | | else: |
|---|
| | |
|---|
| | | 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)) |
|---|
