update cmakelist

雾聪

2024-03-14 0cf5dfec2c8313fc2ed2aab8d10bf3dc4b9c283f

 funasr/models/contextual_paraformer/model.py

@@ -63,7 +63,6 @@
        crit_attn_smooth = kwargs.get("crit_attn_smooth", 0.0)
        bias_encoder_dropout_rate = kwargs.get("bias_encoder_dropout_rate", 0.0)

        pdb.set_trace()
        if bias_encoder_type == 'lstm':
            self.bias_encoder = torch.nn.LSTM(inner_dim, inner_dim, 1, batch_first=True, dropout=bias_encoder_dropout_rate)
            self.bias_embed = torch.nn.Embedding(self.vocab_size, inner_dim)
@@ -81,7 +80,6 @@
        if self.crit_attn_weight > 0:
            self.attn_loss = torch.nn.L1Loss()
        self.crit_attn_smooth = crit_attn_smooth
        pdb.set_trace()


    def forward(
@@ -104,17 +102,16 @@
            text_lengths = text_lengths[:, 0]
        if len(speech_lengths.size()) > 1:
            speech_lengths = speech_lengths[:, 0]
        pdb.set_trace()

        batch_size = speech.shape[0]

        hotword_pad = kwargs.get("hotword_pad")
        hotword_lengths = kwargs.get("hotword_lengths")
        dha_pad = kwargs.get("dha_pad")
        pdb.set_trace()
        # dha_pad = kwargs.get("dha_pad")

        # 1. Encoder
        encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)

        pdb.set_trace()
        loss_ctc, cer_ctc = None, None
        
        stats = dict()
@@ -129,12 +126,11 @@
            stats["loss_ctc"] = loss_ctc.detach() if loss_ctc is not None else None
            stats["cer_ctc"] = cer_ctc
        
        pdb.set_trace()
        # 2b. Attention decoder branch
        loss_att, acc_att, cer_att, wer_att, loss_pre, loss_ideal = self._calc_att_clas_loss(
            encoder_out, encoder_out_lens, text, text_lengths, hotword_pad, hotword_lengths
        )
        pdb.set_trace()

        # 3. CTC-Att loss definition
        if self.ctc_weight == 0.0:
            loss = loss_att + loss_pre * self.predictor_weight
@@ -172,38 +168,33 @@
    ):
        encoder_out_mask = (~make_pad_mask(encoder_out_lens, maxlen=encoder_out.size(1))[:, None, :]).to(
            encoder_out.device)
        pdb.set_trace()

        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
        pdb.set_trace()

        pre_acoustic_embeds, pre_token_length, _, _ = self.predictor(encoder_out, ys_pad, encoder_out_mask,
                                                                     ignore_id=self.ignore_id)
        pdb.set_trace()
        # -1. bias encoder
        if self.use_decoder_embedding:
            hw_embed = self.decoder.embed(hotword_pad)
        else:
            hw_embed = self.bias_embed(hotword_pad)
        pdb.set_trace()

        hw_embed, (_, _) = self.bias_encoder(hw_embed)
        pdb.set_trace()
        _ind = np.arange(0, hotword_pad.shape[0]).tolist()
        selected = hw_embed[_ind, [i - 1 for i in hotword_lengths.detach().cpu().tolist()]]
        contextual_info = selected.squeeze(0).repeat(ys_pad.shape[0], 1, 1).to(ys_pad.device)
        pdb.set_trace()

        # 0. sampler
        decoder_out_1st = None
        if self.sampling_ratio > 0.0:
            if self.step_cur < 2:
                logging.info("enable sampler in paraformer, sampling_ratio: {}".format(self.sampling_ratio))

            sematic_embeds, decoder_out_1st = self.sampler(encoder_out, encoder_out_lens, ys_pad, ys_pad_lens,
                                                           pre_acoustic_embeds, contextual_info)
        else:
            if self.step_cur < 2:
                logging.info("disable sampler in paraformer, sampling_ratio: {}".format(self.sampling_ratio))
            sematic_embeds = pre_acoustic_embeds
        pdb.set_trace()

        # 1. Forward decoder
        decoder_outs = self.decoder(
            encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, contextual_info=contextual_info
@@ -219,7 +210,7 @@
            loss_ideal = None
        '''
        loss_ideal = None
        pdb.set_trace()

        if decoder_out_1st is None:
            decoder_out_1st = decoder_out
        # 2. Compute attention loss
@@ -296,10 +287,11 @@
                                                               enforce_sorted=False)
            _, (h_n, _) = self.bias_encoder(hw_embed)
            hw_embed = h_n.repeat(encoder_out.shape[0], 1, 1)
        

        decoder_outs = self.decoder(
            encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, contextual_info=hw_embed, clas_scale=clas_scale
        )

        decoder_out = decoder_outs[0]
        decoder_out = torch.log_softmax(decoder_out, dim=-1)
        return decoder_out, ys_pad_lens
@@ -313,38 +305,42 @@
                 **kwargs,
                 ):
        # init beamsearch

        is_use_ctc = kwargs.get("decoding_ctc_weight", 0.0) > 0.00001 and self.ctc != None
        is_use_lm = kwargs.get("lm_weight", 0.0) > 0.00001 and kwargs.get("lm_file", None) is not None
        if self.beam_search is None and (is_use_lm or is_use_ctc):
            logging.info("enable beam_search")
            self.init_beam_search(**kwargs)
            self.nbest = kwargs.get("nbest", 1)
        

        meta_data = {}
        
        # extract fbank feats
        time1 = time.perf_counter()

        audio_sample_list = load_audio_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000))

        time2 = time.perf_counter()
        meta_data["load_data"] = f"{time2 - time1:0.3f}"

        speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"),
                                               frontend=frontend)
        time3 = time.perf_counter()
        meta_data["extract_feat"] = f"{time3 - time2:0.3f}"
        meta_data[
            "batch_data_time"] = speech_lengths.sum().item() * frontend.frame_shift * frontend.lfr_n / 1000
        

        speech = speech.to(device=kwargs["device"])
        speech_lengths = speech_lengths.to(device=kwargs["device"])

        # hotword
        self.hotword_list = self.generate_hotwords_list(kwargs.get("hotword", None), tokenizer=tokenizer, frontend=frontend)
        

        # Encoder
        encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
        if isinstance(encoder_out, tuple):
            encoder_out = encoder_out[0]
        

        # predictor
        predictor_outs = self.calc_predictor(encoder_out, encoder_out_lens)
        pre_acoustic_embeds, pre_token_length, alphas, pre_peak_index = predictor_outs[0], predictor_outs[1], \
@@ -352,8 +348,7 @@
        pre_token_length = pre_token_length.round().long()
        if torch.max(pre_token_length) < 1:
            return []


        
        decoder_outs = self.cal_decoder_with_predictor(encoder_out, encoder_out_lens,
                                                                 pre_acoustic_embeds,
                                                                 pre_token_length,
@@ -385,9 +380,11 @@
                nbest_hyps = [Hypothesis(yseq=yseq, score=score)]
            for nbest_idx, hyp in enumerate(nbest_hyps):
                ibest_writer = None
                if ibest_writer is None and kwargs.get("output_dir") is not None:
                    writer = DatadirWriter(kwargs.get("output_dir"))
                    ibest_writer = writer[f"{nbest_idx + 1}best_recog"]
                if kwargs.get("output_dir") is not None:
                    if not hasattr(self, "writer"):
                        self.writer = DatadirWriter(kwargs.get("output_dir"))
                    ibest_writer = self.writer[f"{nbest_idx + 1}best_recog"]
    
                # remove sos/eos and get results
                last_pos = -1
                if isinstance(hyp.yseq, list):