python/FunASR-XL.git

			@@ -29,6 +29,18 @@
			self_attention_dropout_rate: 0.0
			src_attention_dropout_rate: 0.0

			# frontend related
			frontend: wav_frontend
			frontend_conf:
			fs: 16000
			window: hamming
			n_mels: 80
			frame_length: 25
			frame_shift: 10
			lfr_m: 1
			lfr_n: 1


			# hybrid CTC/attention
			model: paraformer
			model_conf:
			@@ -42,7 +54,7 @@
			accum_grad: 2
			grad_clip: 5
			patience: none
			max_epoch: 50
			max_epoch: 150
			val_scheduler_criterion:
			- valid
			- acc
			@@ -82,10 +94,8 @@
			l_order: 1
			r_order: 1

			log_interval: 50
			normalize: None

			dataset_conf:
			data_types: sound,text
			shuffle: True
			shuffle_conf:
			shuffle_size: 2048
			@@ -93,4 +103,7 @@
			batch_conf:
			batch_type: token
			batch_size: 25000
			num_workers: 8
			num_workers: 8

			log_interval: 50
			normalize: None