python/FunASR-XL.git

			@@ -385,13 +385,6 @@

			super().__init__()

			if specaug is not None:
			specaug_class = tables.specaug_classes.get(specaug)
			specaug = specaug_class(**specaug_conf)
			if normalize is not None:
			normalize_class = tables.normalize_classes.get(normalize)
			normalize = normalize_class(**normalize_conf)

			# audio encoder
			hub = audio_encoder_conf.get("hub", None)
			if hub == "ms":
			@@ -422,23 +415,23 @@
			# llm
			hub = llm_conf.get("hub", "hf")
			self.llm = None
			# if hub == "hf":
			# from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig
			#
			# init_param_path = llm_conf.get("init_param_path", "vicuna-7b-v1.5")
			#
			# model = AutoModelForCausalLM.from_pretrained(
			# init_param_path,
			# load_in_8bit=None,
			# device_map=None,
			# use_cache=None,
			# )
			# freeze = llm_conf.get("freeze", True)
			# if freeze:
			# for name, param in model.named_parameters():
			# param.requires_grad = False
			# model.eval()
			# self.llm = model
			if hub == "hf":
			from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig

			init_param_path = llm_conf.get("init_param_path", "vicuna-7b-v1.5")

			model = AutoModelForCausalLM.from_pretrained(
			init_param_path,
			load_in_8bit=None,
			device_map=None,
			use_cache=None,
			)
			freeze = llm_conf.get("freeze", True)
			if freeze:
			for name, param in model.named_parameters():
			param.requires_grad = False
			model.eval()
			self.llm = model

			# adaptor
			adaptor_class = tables.adaptor_classes.get(audio_adaptor)
			@@ -446,21 +439,6 @@
			audio_adaptor = adaptor_class(**audio_adaptor_conf)

			self.audio_adaptor = audio_adaptor

			self.blank_id = blank_id
			self.sos = sos if sos is not None else vocab_size - 1
			self.eos = eos if eos is not None else vocab_size - 1
			self.vocab_size = vocab_size
			self.ignore_id = ignore_id
			self.specaug = specaug
			self.normalize = normalize

			self.criterion_att = LabelSmoothingLoss(
			size=vocab_size,
			padding_idx=ignore_id,
			smoothing=lsm_weight,
			normalize_length=length_normalized_loss,
			)

			self.error_calculator = None

			@@ -490,31 +468,44 @@
			if len(speech_lengths.size()) > 1:
			speech_lengths = speech_lengths[:, 0]

			batch_size = speech.shape[0]
			batch_size, frames, _ = speech.shape

			# audio encoder
			encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
			encoder_out, encoder_out_lens = self.audio_encoder(speech.permute(0, 2, 1), speech_lengths)

			# audio_adaptor
			encoder_out = self.audio_adaptor(encoder_out)
			encoder_out, encoder_out_lens = self.audio_adaptor(encoder_out, encoder_out_lens)

			input_ids[input_ids == -1] = 0
			input_ids[input_ids == -100] = 0
			if hasattr(self.llm.model, "embed_tokens"):
			inputs_embeds = self.llm.model.embed_tokens(input_ids)
			elif hasattr(self.llm.model.model, "embed_tokens"):
			inputs_embeds = self.llm.model.model.embed_tokens(input_ids)
			else:
			inputs_embeds = self.llm.model.model.model.embed_tokens(input_ids)
			input_ids[input_ids < 0] = 0
			inputs_embeds = self.llm.model.get_input_embeddings()(input_ids)

			batch_size, token_num, dims = inputs_embeds.shape
			_, l, _ = encoder_out.shape
			fbank_mask[fbank_mask < 0] = 0
			fbank_fake_lens = fbank_mask.sum(-1).to(torch.int32)
			# _, l, _ = encoder_out.shape
			for batch_idx in range(batch_size):
			fbank_beg_idx = fbank_beg[batch_idx, 0].item()
			inputs_embeds[batch_idx, fbank_beg_idx : fbank_beg_idx + l, :] = encoder_out[
			batch_idx, :l, :
			]

			fbank_fake_len = fbank_fake_lens[batch_idx].item()
			fbank_beg_idx = fbank_beg[batch_idx, 0].item()
			min_len = min(fbank_fake_len, inputs_embeds.shape[1] - fbank_beg_idx)
			fbank_fake_len = encoder_out_lens[batch_idx].item()
			min_len = min(fbank_fake_len, inputs_embeds.shape[1] - fbank_beg_idx)
			try:
			inputs_embeds[batch_idx, fbank_beg_idx : fbank_beg_idx + min_len, :] = encoder_out[
			batch_idx, :min_len, :
			]
			except Exception as e:
			logging.error(f"{str(e)}, {traceback.format_exc()}")
			logging.info(
			f"batch_idx: {batch_idx}, inputs_embeds: {inputs_embeds.shape}, fbank_beg_idx: {fbank_beg_idx}, min_len: {min_len}, fbank_fake_len: {fbank_fake_len}"
			)
			fbank_fake_len = encoder_out_lens[batch_idx].item()
			min_len = min(fbank_fake_len, inputs_embeds.shape[1] - fbank_beg_idx)
			inputs_embeds[batch_idx, fbank_beg_idx : fbank_beg_idx + min_len, :] = encoder_out[
			batch_idx, :min_len, :
			]

			labels_ids[labels_ids == -1] = -100
			model_outputs = self.llm(
			inputs_embeds=inputs_embeds, attention_mask=attention_mask, labels=labels_ids
			)
			@@ -527,26 +518,19 @@
			stats["acc"] = acc_att

			stats["loss"] = torch.clone(loss.detach())
			stats["batch_size"] = batch_size
			stats["batch_size_x_frames"] = frames * batch_size
			stats["batch_size_real_frames"] = speech_lengths.sum().item()
			stats["padding_frames"] = stats["batch_size_x_frames"] - stats["batch_size_real_frames"]
			stats["batch_size_x_tokens"] = token_num * batch_size
			stats["batch_size_real_tokens"] = attention_mask.sum().item()
			stats["padding_tokens"] = stats["batch_size_x_tokens"] - stats["batch_size_real_tokens"]

			# force_gatherable: to-device and to-tensor if scalar for DataParallel
			if self.length_normalized_loss:
			batch_size = int((text_lengths + 1).sum())
			batch_size = int((labels_ids > 0 + 1).sum())
			loss, stats, weight = force_gatherable((loss, stats, batch_size), loss.device)
			return loss, stats, weight

			def encode(
			self,
			speech: torch.Tensor,
			speech_lengths: torch.Tensor,
			**kwargs,
			):
			speech = speech.permute(0, 2, 1)
			res = self.audio_encoder(speech)
			if isinstance(res, (list, tuple)):
			encoder_out, encoder_out_lens = res[0], res[1]
			else:
			encoder_out, encoder_out_lens = res, speech_lengths
			return encoder_out, encoder_out_lens

			def inference(
			self,