python/FunASR-XL.git

			@@ -255,8 +255,10 @@
			if param_dict is not None:
			hotword_list_or_file = param_dict.get('hotword')
			export_mode = param_dict.get("export_mode", False)
			clas_scale = param_dict.get('clas_scale', 1.0)
			else:
			hotword_list_or_file = None
			clas_scale = 1.0

			if kwargs.get("device", None) == "cpu":
			ngpu = 0
			@@ -289,6 +291,7 @@
			penalty=penalty,
			nbest=nbest,
			hotword_list_or_file=hotword_list_or_file,
			clas_scale=clas_scale,
			)

			speech2text = Speech2TextParaformer(**speech2text_kwargs)
			@@ -617,10 +620,27 @@
			sorted_data = sorted(data_with_index, key=lambda x: x[0][1] - x[0][0])
			results_sorted = []

			if not len(sorted_data):
			key = keys[0]
			# no active segments after VAD
			if writer is not None:
			# Write empty results
			ibest_writer["token"][key] = ""
			ibest_writer["token_int"][key] = ""
			ibest_writer["vad"][key] = ""
			ibest_writer["text"][key] = ""
			ibest_writer["text_with_punc"][key] = ""
			if use_timestamp:
			ibest_writer["time_stamp"][key] = ""

			logging.info("decoding, utt: {}, empty speech".format(key))
			continue

			batch_size_token_ms = batch_size_token*60
			if speech2text.device == "cpu":
			batch_size_token_ms = 0
			batch_size_token_ms = max(batch_size_token_ms, sorted_data[0][0][1] - sorted_data[0][0][0])
			if len(sorted_data) > 0 and len(sorted_data[0]) > 0:
			batch_size_token_ms = max(batch_size_token_ms, sorted_data[0][0][1] - sorted_data[0][0][0])

			batch_size_token_ms_cum = 0
			beg_idx = 0
			@@ -1349,10 +1369,7 @@
			left_context=left_context,
			right_context=right_context,
			)
			speech2text = Speech2TextTransducer.from_pretrained(
			model_tag=model_tag,
			**speech2text_kwargs,
			)
			speech2text = Speech2TextTransducer(**speech2text_kwargs)

			def _forward(data_path_and_name_and_type,
			raw_inputs: Union[np.ndarray, torch.Tensor] = None,