Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add

游雁

2023-06-15 a2af08c32d96b136d3d91d28a6da0ba6ea52e00f

 funasr/bin/asr_infer.py

@@ -493,9 +493,9 @@
            else:
                if pre_token_length[i] == 0:
                    yseq = torch.tensor(
                        [self.asr_model.sos] + [self.asr_model.eos], device=yseq.device
                        [self.asr_model.sos] + [self.asr_model.eos], device=pre_acoustic_embeds.device
                    )
                    score = torch.tensor(0.0, device=yseq.device)
                    score = torch.tensor(0.0, device=pre_acoustic_embeds.device)
                else:
                    yseq = am_scores.argmax(dim=-1)
                    score = am_scores.max(dim=-1)[0]
@@ -1512,8 +1512,13 @@
        if isinstance(speech, np.ndarray):
            speech = torch.tensor(speech)
        
        feats = speech.unsqueeze(0).to(getattr(torch, self.dtype))
        feats_lengths = feats.new_full([1], dtype=torch.long, fill_value=feats.size(1))
        if self.frontend is not None:
            speech = torch.unsqueeze(speech, axis=0)
            speech_lengths = speech.new_full([1], dtype=torch.long, fill_value=speech.size(1))
            feats, feats_lengths = self.frontend(speech, speech_lengths)
        else:                
            feats = speech.unsqueeze(0).to(getattr(torch, self.dtype))
            feats_lengths = feats.new_full([1], dtype=torch.long, fill_value=feats.size(1))
        
        if self.asr_model.normalize is not None:
            feats, feats_lengths = self.asr_model.normalize(feats, feats_lengths)
@@ -1538,14 +1543,19 @@
        
        if isinstance(speech, np.ndarray):
            speech = torch.tensor(speech)
        
        feats = speech.unsqueeze(0).to(getattr(torch, self.dtype))
        feats_lengths = feats.new_full([1], dtype=torch.long, fill_value=feats.size(1))

        if self.frontend is not None:
            speech = torch.unsqueeze(speech, axis=0)
            speech_lengths = speech.new_full([1], dtype=torch.long, fill_value=speech.size(1))
            feats, feats_lengths = self.frontend(speech, speech_lengths)
        else:                
            feats = speech.unsqueeze(0).to(getattr(torch, self.dtype))
            feats_lengths = feats.new_full([1], dtype=torch.long, fill_value=feats.size(1))
        
        feats = to_device(feats, device=self.device)
        feats_lengths = to_device(feats_lengths, device=self.device)
        
        enc_out, _ = self.asr_model.encoder(feats, feats_lengths)
        enc_out, _, _ = self.asr_model.encoder(feats, feats_lengths)
        
        nbest_hyps = self.beam_search(enc_out[0])