{ "schema_version": 1, "model_type": "offline_zipformer_transducer", "model_args": { "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, "feature_dim": 80, "attention_decoder_dim": 512, "attention_decoder_num_layers": 6, "attention_decoder_attention_dim": 512, "attention_decoder_num_heads": 8, "attention_decoder_feedforward_dim": 2048, "blank_id": 0, "unk_id": 7, "vocab_size": 500 }, "inference": { "sample_rate": 16000, "feature_type": "kaldifeat.Fbank", "num_mel_bins": 80, "dither": 0, "snip_edges": false, "high_freq": -400, "precision": "fp32", "decoding_method": "modified_beam_search", "beam_size": 4, "voicea_postprocessing": true, "min_input_seconds": 1, "long_chunk_seconds": 30, "long_chunk_batch_size": 512, "batch_size": 2048, "batch_audio_seconds": 5000, "torch_threads": 16 }, "expected": { "parameters": 65551059, "checkpoint_sha256": "b0475d24e50f810fbcf997e66061243a1fe212251f6d032457b2711641906c01", "tokens_sha256": "a238b7a0fa67aa6be998ca13dd129d69c50639970583e32232dd149e5448210a" } }