python/FunASR-XL.git

			@@ -341,3 +341,321 @@
			ibest_writer["text"][key[0]] = text

			return results, meta_data


			@tables.register("model_classes", "LLMASR2")
			class LLMASR2(nn.Module):
			""" """

			def __init__(
			self,
			specaug: str = None,
			specaug_conf: dict = None,
			normalize: str = None,
			normalize_conf: dict = None,
			audio_encoder: str = None,
			audio_encoder_conf: dict = None,
			audio_adaptor: str = None,
			audio_adaptor_conf: dict = None,
			decoder: str = None,
			decoder_conf: dict = None,
			ctc: str = None,
			ctc_conf: dict = None,
			ctc_weight: float = 0.5,
			llm: str = None,
			llm_conf: dict = None,
			input_size: int = 80,
			vocab_size: int = -1,
			ignore_id: int = -1,
			blank_id: int = 0,
			sos: int = 1,
			eos: int = 2,
			lsm_weight: float = 0.0,
			length_normalized_loss: bool = False,
			report_cer: bool = True,
			report_wer: bool = True,
			sym_space: str = "<space>",
			sym_blank: str = "<blank>",
			# extract_feats_in_collect_stats: bool = True,
			share_embedding: bool = False,
			# preencoder: Optional[AbsPreEncoder] = None,
			# postencoder: Optional[AbsPostEncoder] = None,
			**kwargs,
			):

			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":
			from funasr import AutoModel

			model = AutoModel(model=audio_encoder, model_revision="master")
			# frontend = model.kwargs.get("frontend")
			audio_encoder_output_size = model.model.encoder_output_size

			audio_encoder = model.model.model.encoder

			# self.frontend = frontend

			elif hub == "hf":
			pass
			else:
			encoder_class = tables.encoder_classes.get(audio_encoder)
			audio_encoder = encoder_class(input_size=input_size, **audio_encoder_conf)
			audio_encoder_output_size = audio_encoder.output_size()
			freeze = audio_encoder_conf.get("freeze", True)
			if freeze:
			for name, param in audio_encoder.named_parameters():
			param.requires_grad = False
			audio_encoder.eval()

			self.audio_encoder = audio_encoder

			# 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

			# adaptor
			adaptor_class = tables.adaptor_classes.get(audio_adaptor)
			audio_adaptor_conf["encoder_dim"] = audio_encoder_output_size
			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

			self.length_normalized_loss = length_normalized_loss
			self.beam_search = None

			def forward(
			self,
			speech: torch.Tensor,
			speech_lengths: torch.Tensor,
			input_ids: torch.Tensor,
			attention_mask: torch.Tensor,
			labels_ids: torch.Tensor,
			fbank_beg: torch.Tensor,
			fbank_mask: torch.Tensor,
			**kwargs,
			) -> Tuple[torch.Tensor, Dict[str, torch.Tensor], torch.Tensor]:
			"""Encoder + Decoder + Calc loss
			Args:
			speech: (Batch, Length, ...)
			speech_lengths: (Batch, )
			text: (Batch, Length)
			text_lengths: (Batch,)
			"""
			# import pdb;
			# pdb.set_trace()
			if len(speech_lengths.size()) > 1:
			speech_lengths = speech_lengths[:, 0]

			batch_size = speech.shape[0]

			# audio encoder
			encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)

			# audio_adaptor
			encoder_out = self.audio_adaptor(encoder_out)

			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)

			batch_size, token_num, dims = inputs_embeds.shape
			_, 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, :
			]

			model_outputs = self.llm(
			inputs_embeds=inputs_embeds, attention_mask=attention_mask, labels=labels_ids
			)
			loss = model_outputs.loss

			stats = {}
			with torch.no_grad():
			preds = torch.argmax(model_outputs.logits, -1)
			acc_att = compute_accuracy(preds[:, :-1], labels_ids[:, 1:], ignore_label=-100)
			stats["acc"] = acc_att

			stats["loss"] = torch.clone(loss.detach())

			# force_gatherable: to-device and to-tensor if scalar for DataParallel
			if self.length_normalized_loss:
			batch_size = int((text_lengths + 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,
			data_in,
			data_lengths=None,
			key: list = None,
			tokenizer=None,
			frontend=None,
			**kwargs,
			):

			prompt = kwargs.get("prompt", "Transcribe speech to text.")

			if kwargs.get("batch_size", 1) > 1:
			raise NotImplementedError("batch decoding is not implemented")

			meta_data = {}
			if (
			isinstance(data_in, torch.Tensor) and kwargs.get("data_type", "sound") == "fbank"
			): # fbank
			speech, speech_lengths = data_in, data_lengths
			if len(speech.shape) < 3:
			speech = speech[None, :, :]
			if speech_lengths is None:
			speech_lengths = speech.shape[1]
			else:
			# 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),
			data_type=kwargs.get("data_type", "sound"),
			tokenizer=tokenizer,
			)
			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"])

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

			# adaptor
			encoder_out = self.audio_adaptor(encoder_out)

			prompt_pre = "USER: \nINSTRUCTION: {}\nINPUT: ".format(prompt)
			prompt_ids = tokenizer.encode(prompt_pre)
			prompt_length = len(prompt_ids)
			prompt_ids = torch.tensor(prompt_ids, dtype=torch.int64).to(kwargs["device"])

			if hasattr(self.llm.model, "embed_tokens"):
			inputs_embeds = self.llm.model.embed_tokens(prompt_ids)
			elif hasattr(self.llm.model.model, "embed_tokens"):
			inputs_embeds = self.llm.model.model.embed_tokens(prompt_ids)
			else:
			inputs_embeds = self.llm.model.model.model.embed_tokens(prompt_ids)

			inputs_embeds = torch.cat(
			(inputs_embeds[None, :, :], encoder_out), dim=1
			) # [prompt, audio]
			attention_mask = torch.ones(inputs_embeds.size()[:-1], dtype=torch.long).to(
			kwargs["device"]
			)

			preds = self.llm.generate(
			inputs_embeds=inputs_embeds,
			max_length=kwargs.get("max_length", 200),
			max_new_tokens=kwargs.get("max_new_tokens", 200),
			num_beams=kwargs.get("num_beams", 4),
			do_sample=kwargs.get("do_sample", False),
			min_length=kwargs.get("min_length", 1),
			top_p=kwargs.get("top_p", 1.0),
			repetition_penalty=kwargs.get("repetition_penalty", 1.0),
			length_penalty=kwargs.get("length_penalty", 1.0),
			temperature=kwargs.get("temperature", 1.0),
			attention_mask=attention_mask,
			bos_token_id=tokenizer.bos_token_id,
			eos_token_id=tokenizer.eos_token_id,
			pad_token_id=tokenizer.pad_token_id,
			)

			text = tokenizer.batch_decode(preds, add_special_tokens=False, skip_special_tokens=True)

			text = text[0].split(": ")[-1]
			text = text.strip()

			# preds = torch.argmax(model_outputs.logits, -1)

			ibest_writer = None
			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"{0 + 1}best_recog"]

			results = []
			result_i = {"key": key[0], "text": text}
			results.append(result_i)

			if ibest_writer is not None:
			ibest_writer["text"][key[0]] = text

			return results, meta_data