Method encode

audio.py:427–443

(self, input_audios: Tensor, input_audio_lengths: Tensor, audio_span_tokens: List)

        return x, bos, eos

    def encode(self, input_audios: Tensor, input_audio_lengths: Tensor, audio_span_tokens: List):
        real_input_audio_lens = input_audio_lengths[:, 0].tolist()
        max_len_in_batch = max(real_input_audio_lens)
        padding_mask = torch.ones([input_audios.size(0), max_len_in_batch]).to(dtype=self.conv1.weight.dtype,
                                                                               device=self.conv1.weight.device)
        for index in range(len(input_audios)):
            padding_mask[index, :input_audio_lengths[index][0].item()] = 0
        x, bos, eos = self(input_audios, padding_mask,input_audio_lengths)
        output_audios = []
        for i in range(len(audio_span_tokens)):
            audio_span = audio_span_tokens[i]
            audio = x[i][:audio_span-2]
            if bos is not None:
                audio = torch.concat([bos, audio, eos])
            assert len(audio) == audio_span
            output_audios.append(audio)
        return output_audios