{ "num_encoder_layers": "2,2,3,4,3,2", "downsampling_factor": "1,2,4,8,4,2", "feedforward_dim": "512,768,1024,1536,1024,768", "num_heads": "4,4,4,8,4,4", "encoder_dim": "192,256,384,512,384,256", "query_head_dim": "32", "value_head_dim": "12", "pos_head_dim": "4", "pos_dim": 48, "encoder_unmasked_dim": "192,192,256,256,256,192", "cnn_module_kernel": "31,31,15,15,15,31", "decoder_dim": 512, "joiner_dim": 512, "context_size": 3, "causal": false, "chunk_size": "-1", "left_context_frames": "-1", "use_transducer": true, "use_ctc": false, "use_attention_decoder": false, "use_cr_ctc": false }