python/FunASR-XL.git

			@@ -29,7 +29,7 @@
			from funasr.models.transformer.utils.add_sos_eos import add_sos_eos
			from funasr.models.transformer.utils.nets_utils import make_pad_mask, pad_list
			from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank

			import pdb

			if LooseVersion(torch.__version__) >= LooseVersion("1.6.0"):
			from torch.cuda.amp import autocast
			@@ -62,7 +62,6 @@
			crit_attn_weight = kwargs.get("crit_attn_weight", 0.0)
			crit_attn_smooth = kwargs.get("crit_attn_smooth", 0.0)
			bias_encoder_dropout_rate = kwargs.get("bias_encoder_dropout_rate", 0.0)


			if bias_encoder_type == 'lstm':
			self.bias_encoder = torch.nn.LSTM(inner_dim, inner_dim, 1, batch_first=True, dropout=bias_encoder_dropout_rate)
			@@ -103,17 +102,16 @@
			text_lengths = text_lengths[:, 0]
			if len(speech_lengths.size()) > 1:
			speech_lengths = speech_lengths[:, 0]


			batch_size = speech.shape[0]

			hotword_pad = kwargs.get("hotword_pad")
			hotword_lengths = kwargs.get("hotword_lengths")
			dha_pad = kwargs.get("dha_pad")


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


			loss_ctc, cer_ctc = None, None

			stats = dict()
			@@ -128,12 +126,11 @@
			stats["loss_ctc"] = loss_ctc.detach() if loss_ctc is not None else None
			stats["cer_ctc"] = cer_ctc


			# 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
			)


			# 3. CTC-Att loss definition
			if self.ctc_weight == 0.0:
			loss = loss_att + loss_pre * self.predictor_weight
			@@ -171,22 +168,24 @@
			):
			encoder_out_mask = (~make_pad_mask(encoder_out_lens, maxlen=encoder_out.size(1))[:, None, :]).to(
			encoder_out.device)

			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, _, _ = self.predictor(encoder_out, ys_pad, encoder_out_mask,
			ignore_id=self.ignore_id)

			# -1. bias encoder
			if self.use_decoder_embedding:
			hw_embed = self.decoder.embed(hotword_pad)
			else:
			hw_embed = self.bias_embed(hotword_pad)

			hw_embed, (_, _) = self.bias_encoder(hw_embed)
			_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)


			# 0. sampler
			decoder_out_1st = None
			if self.sampling_ratio > 0.0:
			@@ -195,7 +194,7 @@
			pre_acoustic_embeds, contextual_info)
			else:
			sematic_embeds = pre_acoustic_embeds


			# 1. Forward decoder
			decoder_outs = self.decoder(
			encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, contextual_info=contextual_info
			@@ -211,7 +210,7 @@
			loss_ideal = None
			'''
			loss_ideal = None


			if decoder_out_1st is None:
			decoder_out_1st = decoder_out
			# 2. Compute attention loss
			@@ -288,10 +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
			@@ -305,38 +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], \
			@@ -344,8 +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,