update

speech_asr

2023-04-11 23bc5dee4e88ef8b5d0c0d64d2e188c054422e8b

 funasr/models/e2e_uni_asr.py

@@ -23,6 +23,7 @@
from funasr.models.postencoder.abs_postencoder import AbsPostEncoder
from funasr.models.preencoder.abs_preencoder import AbsPreEncoder
from funasr.models.specaug.abs_specaug import AbsSpecAug
from funasr.models.base_model import FunASRModel
from funasr.layers.abs_normalize import AbsNormalize
from funasr.torch_utils.device_funcs import force_gatherable
from funasr.train.abs_espnet_model import AbsESPnetModel
@@ -38,7 +39,7 @@
        yield


class UniASR(AbsESPnetModel):
class UniASR(FunASRModel):
    """
    Author: Speech Lab, Alibaba Group, China
    """
@@ -198,16 +199,15 @@

        # for data-parallel
        text = text[:, : text_lengths.max()]
        speech = speech[:, :speech_lengths.max(), :]
        speech = speech[:, :speech_lengths.max()]

        ind = self.encoder.overlap_chunk_cls.random_choice(self.training, decoding_ind)
        speech_raw = speech.clone().to(speech.device)
        # 1. Encoder
        if self.enable_maas_finetune:
            with torch.no_grad():
                encoder_out, encoder_out_lens = self.encode(speech, speech_lengths, ind=ind)
                speech_raw, encoder_out, encoder_out_lens = self.encode(speech, speech_lengths, ind=ind)
        else:
            encoder_out, encoder_out_lens = self.encode(speech, speech_lengths, ind=ind)
            speech_raw, encoder_out, encoder_out_lens = self.encode(speech, speech_lengths, ind=ind)

        intermediate_outs = None
        if isinstance(encoder_out, tuple):
@@ -486,7 +486,7 @@
            # 3. Normalization for feature: e.g. Global-CMVN, Utterance-CMVN
            if self.normalize is not None:
                feats, feats_lengths = self.normalize(feats, feats_lengths)

        speech_raw = feats.clone().to(feats.device)
        # Pre-encoder, e.g. used for raw input data
        if self.preencoder is not None:
            feats, feats_lengths = self.preencoder(feats, feats_lengths)
@@ -523,7 +523,7 @@
        if intermediate_outs is not None:
            return (encoder_out, intermediate_outs), encoder_out_lens

        return encoder_out, encoder_out_lens
        return speech_raw, encoder_out, encoder_out_lens

    def encode2(
        self,