train

游雁

2023-05-16 3d9f094e9652d4b84894c6fd4eae39a4a753b0f0

 funasr/models/e2e_asr_paraformer.py

@@ -326,9 +326,8 @@

        encoder_out_mask = (~make_pad_mask(encoder_out_lens, maxlen=encoder_out.size(1))[:, None, :]).to(
            encoder_out.device)
        pre_acoustic_embeds, pre_token_length, alphas, pre_peak_index = self.predictor(encoder_out, None,
                                                                                       encoder_out_mask,
                                                                                       ignore_id=self.ignore_id)
        pre_acoustic_embeds, pre_token_length, alphas, pre_peak_index = self.predictor(encoder_out, None, encoder_out_mask,
                                                                                  ignore_id=self.ignore_id)
        return pre_acoustic_embeds, pre_token_length, alphas, pre_peak_index

    def cal_decoder_with_predictor(self, encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens):
@@ -659,6 +658,10 @@
            self, speech: torch.Tensor, speech_lengths: torch.Tensor, cache: dict = None
    ) -> Tuple[torch.Tensor, torch.Tensor]:
        """Frontend + Encoder. Note that this method is used by asr_inference.py
<<<<<<< HEAD
=======

>>>>>>> 4cd79db451786548d8a100f25c3b03da0eb30f4b
        Args:
                speech: (Batch, Length, ...)
                speech_lengths: (Batch, )
@@ -906,9 +909,9 @@
        self.step_cur += 1
        # for data-parallel
        text = text[:, : text_lengths.max()]
        speech = speech[:, :speech_lengths.max(), :]
        speech = speech[:, :speech_lengths.max()]
        if embed is not None:
            embed = embed[:, :embed_lengths.max(), :]
            embed = embed[:, :embed_lengths.max()]

        # 1. Encoder
        encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
@@ -1097,9 +1100,8 @@
        if self.predictor_bias == 1:
            _, ys_pad = add_sos_eos(ys_pad, self.sos, self.eos, self.ignore_id)
            ys_pad_lens = ys_pad_lens + self.predictor_bias
        pre_acoustic_embeds, pre_token_length, _, pre_peak_index, _ = self.predictor(encoder_out, ys_pad,
                                                                                     encoder_out_mask,
                                                                                     ignore_id=self.ignore_id)
        pre_acoustic_embeds, pre_token_length, _, pre_peak_index, _ = self.predictor(encoder_out, ys_pad, encoder_out_mask,
                                                                                  ignore_id=self.ignore_id)

        # 0. sampler
        decoder_out_1st = None