| | |
|---|
| | | 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) |
|---|
