{ "format_version": 2, "checkpoint_path": "MOSS-Audio-Tokenizer-Nano", "files": { "encode": "moss_audio_tokenizer_encode.onnx", "decode_full": "moss_audio_tokenizer_decode_full.onnx", "decode_step": "moss_audio_tokenizer_decode_step.onnx" }, "external_data_files": { "moss_audio_tokenizer_encode.onnx": [ "moss_audio_tokenizer_encode.data" ], "moss_audio_tokenizer_decode_full.onnx": [ "moss_audio_tokenizer_decode_shared.data" ], "moss_audio_tokenizer_decode_step.onnx": [ "moss_audio_tokenizer_decode_shared.data" ] }, "codec_config": { "sample_rate": 48000, "channels": 2, "downsample_rate": 3840, "num_quantizers": 16 }, "onnx": { "opset": 17, "encode_input_names": [ "waveform", "input_lengths" ], "encode_output_names": [ "audio_codes", "audio_code_lengths" ], "decode_input_names": [ "audio_codes", "audio_code_lengths" ], "decode_output_names": [ "audio", "audio_lengths" ], "decode_step_input_names": [ "audio_codes", "audio_code_lengths", "transformer_offset_0", "transformer_offset_1", "transformer_offset_2", "transformer_offset_3", "attn_offset_0", "attn_cached_keys_0", "attn_cached_values_0", "attn_cached_positions_0", "attn_offset_1", "attn_cached_keys_1", "attn_cached_values_1", "attn_cached_positions_1", "attn_offset_2", "attn_cached_keys_2", "attn_cached_values_2", "attn_cached_positions_2", "attn_offset_3", "attn_cached_keys_3", "attn_cached_values_3", "attn_cached_positions_3", "attn_offset_4", "attn_cached_keys_4", "attn_cached_values_4", "attn_cached_positions_4", "attn_offset_5", "attn_cached_keys_5", "attn_cached_values_5", "attn_cached_positions_5", "attn_offset_6", "attn_cached_keys_6", "attn_cached_values_6", "attn_cached_positions_6", "attn_offset_7", "attn_cached_keys_7", "attn_cached_values_7", "attn_cached_positions_7", "attn_offset_8", "attn_cached_keys_8", "attn_cached_values_8", "attn_cached_positions_8", "attn_offset_9", "attn_cached_keys_9", "attn_cached_values_9", "attn_cached_positions_9", "attn_offset_10", "attn_cached_keys_10", "attn_cached_values_10", "attn_cached_positions_10", "attn_offset_11", "attn_cached_keys_11", "attn_cached_values_11", "attn_cached_positions_11" ], "decode_step_output_names": [ "audio", "audio_lengths", "transformer_offset_out_0", "transformer_offset_out_1", "transformer_offset_out_2", "transformer_offset_out_3", "attn_offset_out_0", "attn_cached_keys_out_0", "attn_cached_values_out_0", "attn_cached_positions_out_0", "attn_offset_out_1", "attn_cached_keys_out_1", "attn_cached_values_out_1", "attn_cached_positions_out_1", "attn_offset_out_2", "attn_cached_keys_out_2", "attn_cached_values_out_2", "attn_cached_positions_out_2", "attn_offset_out_3", "attn_cached_keys_out_3", "attn_cached_values_out_3", "attn_cached_positions_out_3", "attn_offset_out_4", "attn_cached_keys_out_4", "attn_cached_values_out_4", "attn_cached_positions_out_4", "attn_offset_out_5", "attn_cached_keys_out_5", "attn_cached_values_out_5", "attn_cached_positions_out_5", "attn_offset_out_6", "attn_cached_keys_out_6", "attn_cached_values_out_6", "attn_cached_positions_out_6", "attn_offset_out_7", "attn_cached_keys_out_7", "attn_cached_values_out_7", "attn_cached_positions_out_7", "attn_offset_out_8", "attn_cached_keys_out_8", "attn_cached_values_out_8", "attn_cached_positions_out_8", "attn_offset_out_9", "attn_cached_keys_out_9", "attn_cached_values_out_9", "attn_cached_positions_out_9", "attn_offset_out_10", "attn_cached_keys_out_10", "attn_cached_values_out_10", "attn_cached_positions_out_10", "attn_offset_out_11", "attn_cached_keys_out_11", "attn_cached_values_out_11", "attn_cached_positions_out_11" ] }, "streaming_decode": { "batch_size": 1, "transformer_offsets": [ { "index": 0, "decoder_index": 1, "input_name": "transformer_offset_0", "output_name": "transformer_offset_out_0", "shape": [ 1 ], "dtype": "int32" }, { "index": 1, "decoder_index": 3, "input_name": "transformer_offset_1", "output_name": "transformer_offset_out_1", "shape": [ 1 ], "dtype": "int32" }, { "index": 2, "decoder_index": 5, "input_name": "transformer_offset_2", "output_name": "transformer_offset_out_2", "shape": [ 1 ], "dtype": "int32" }, { "index": 3, "decoder_index": 7, "input_name": "transformer_offset_3", "output_name": "transformer_offset_out_3", "shape": [ 1 ], "dtype": "int32" } ], "attention_caches": [ { "index": 0, "decoder_index": 1, "layer_index": 0, "context": 500, "num_heads": 4, "head_dim": 64, "offset_input_name": "attn_offset_0", "offset_output_name": "attn_offset_out_0", "cached_keys_input_name": "attn_cached_keys_0", "cached_keys_output_name": "attn_cached_keys_out_0", "cached_values_input_name": "attn_cached_values_0", "cached_values_output_name": "attn_cached_values_out_0", "cached_positions_input_name": "attn_cached_positions_0", "cached_positions_output_name": "attn_cached_positions_out_0", "offset_shape": [ 1 ], "cache_shape": [ 1, 4, 500, 64 ], "positions_shape": [ 1, 500 ], "cache_dtype": "float32", "positions_dtype": "int32" }, { "index": 1, "decoder_index": 1, "layer_index": 1, "context": 500, "num_heads": 4, "head_dim": 64, "offset_input_name": "attn_offset_1", "offset_output_name": "attn_offset_out_1", "cached_keys_input_name": "attn_cached_keys_1", "cached_keys_output_name": "attn_cached_keys_out_1", "cached_values_input_name": "attn_cached_values_1", "cached_values_output_name": "attn_cached_values_out_1", "cached_positions_input_name": "attn_cached_positions_1", "cached_positions_output_name": "attn_cached_positions_out_1", "offset_shape": [ 1 ], "cache_shape": [ 1, 4, 500, 64 ], "positions_shape": [ 1, 500 ], "cache_dtype": "float32", "positions_dtype": "int32" }, { "index": 2, "decoder_index": 1, "layer_index": 2, "context": 500, "num_heads": 4, "head_dim": 64, "offset_input_name": "attn_offset_2", "offset_output_name": "attn_offset_out_2", "cached_keys_input_name": "attn_cached_keys_2", "cached_keys_output_name": "attn_cached_keys_out_2", "cached_values_input_name": "attn_cached_values_2", "cached_values_output_name": "attn_cached_values_out_2", "cached_positions_input_name": "attn_cached_positions_2", "cached_positions_output_name": "attn_cached_positions_out_2", "offset_shape": [ 1 ], "cache_shape": [ 1, 4, 500, 64 ], "positions_shape": [ 1, 500 ], "cache_dtype": "float32", "positions_dtype": "int32" }, { "index": 3, "decoder_index": 1, "layer_index": 3, "context": 500, "num_heads": 4, "head_dim": 64, "offset_input_name": "attn_offset_3", "offset_output_name": "attn_offset_out_3", "cached_keys_input_name": "attn_cached_keys_3", "cached_keys_output_name": "attn_cached_keys_out_3", "cached_values_input_name": "attn_cached_values_3", "cached_values_output_name": "attn_cached_values_out_3", "cached_positions_input_name": "attn_cached_positions_3", "cached_positions_output_name": "attn_cached_positions_out_3", "offset_shape": [ 1 ], "cache_shape": [ 1, 4, 500, 64 ], "positions_shape": [ 1, 500 ], "cache_dtype": "float32", "positions_dtype": "int32" }, { "index": 4, "decoder_index": 3, "layer_index": 0, "context": 800, "num_heads": 4, "head_dim": 64, "offset_input_name": "attn_offset_4", "offset_output_name": "attn_offset_out_4", "cached_keys_input_name": "attn_cached_keys_4", "cached_keys_output_name": "attn_cached_keys_out_4", "cached_values_input_name": "attn_cached_values_4", "cached_values_output_name": "attn_cached_values_out_4", "cached_positions_input_name": "attn_cached_positions_4", "cached_positions_output_name": "attn_cached_positions_out_4", "offset_shape": [ 1 ], "cache_shape": [ 1, 4, 800, 64 ], "positions_shape": [ 1, 800 ], "cache_dtype": "float32", "positions_dtype": "int32" }, { "index": 5, "decoder_index": 3, "layer_index": 1, "context": 800, "num_heads": 4, "head_dim": 64, "offset_input_name": "attn_offset_5", "offset_output_name": "attn_offset_out_5", "cached_keys_input_name": "attn_cached_keys_5", "cached_keys_output_name": "attn_cached_keys_out_5", "cached_values_input_name": "attn_cached_values_5", "cached_values_output_name": "attn_cached_values_out_5", "cached_positions_input_name": "attn_cached_positions_5", "cached_positions_output_name": "attn_cached_positions_out_5", "offset_shape": [ 1 ], "cache_shape": [ 1, 4, 800, 64 ], "positions_shape": [ 1, 800 ], "cache_dtype": "float32", "positions_dtype": "int32" }, { "index": 6, "decoder_index": 5, "layer_index": 0, "context": 1200, "num_heads": 4, "head_dim": 64, "offset_input_name": "attn_offset_6", "offset_output_name": "attn_offset_out_6", "cached_keys_input_name": "attn_cached_keys_6", "cached_keys_output_name": "attn_cached_keys_out_6", "cached_values_input_name": "attn_cached_values_6", "cached_values_output_name": "attn_cached_values_out_6", "cached_positions_input_name": "attn_cached_positions_6", "cached_positions_output_name": "attn_cached_positions_out_6", "offset_shape": [ 1 ], "cache_shape": [ 1, 4, 1200, 64 ], "positions_shape": [ 1, 1200 ], "cache_dtype": "float32", "positions_dtype": "int32" }, { "index": 7, "decoder_index": 5, "layer_index": 1, "context": 1200, "num_heads": 4, "head_dim": 64, "offset_input_name": "attn_offset_7", "offset_output_name": "attn_offset_out_7", "cached_keys_input_name": "attn_cached_keys_7", "cached_keys_output_name": "attn_cached_keys_out_7", "cached_values_input_name": "attn_cached_values_7", "cached_values_output_name": "attn_cached_values_out_7", "cached_positions_input_name": "attn_cached_positions_7", "cached_positions_output_name": "attn_cached_positions_out_7", "offset_shape": [ 1 ], "cache_shape": [ 1, 4, 1200, 64 ], "positions_shape": [ 1, 1200 ], "cache_dtype": "float32", "positions_dtype": "int32" }, { "index": 8, "decoder_index": 7, "layer_index": 0, "context": 1600, "num_heads": 4, "head_dim": 64, "offset_input_name": "attn_offset_8", "offset_output_name": "attn_offset_out_8", "cached_keys_input_name": "attn_cached_keys_8", "cached_keys_output_name": "attn_cached_keys_out_8", "cached_values_input_name": "attn_cached_values_8", "cached_values_output_name": "attn_cached_values_out_8", "cached_positions_input_name": "attn_cached_positions_8", "cached_positions_output_name": "attn_cached_positions_out_8", "offset_shape": [ 1 ], "cache_shape": [ 1, 4, 1600, 64 ], "positions_shape": [ 1, 1600 ], "cache_dtype": "float32", "positions_dtype": "int32" }, { "index": 9, "decoder_index": 7, "layer_index": 1, "context": 1600, "num_heads": 4, "head_dim": 64, "offset_input_name": "attn_offset_9", "offset_output_name": "attn_offset_out_9", "cached_keys_input_name": "attn_cached_keys_9", "cached_keys_output_name": "attn_cached_keys_out_9", "cached_values_input_name": "attn_cached_values_9", "cached_values_output_name": "attn_cached_values_out_9", "cached_positions_input_name": "attn_cached_positions_9", "cached_positions_output_name": "attn_cached_positions_out_9", "offset_shape": [ 1 ], "cache_shape": [ 1, 4, 1600, 64 ], "positions_shape": [ 1, 1600 ], "cache_dtype": "float32", "positions_dtype": "int32" }, { "index": 10, "decoder_index": 7, "layer_index": 2, "context": 1600, "num_heads": 4, "head_dim": 64, "offset_input_name": "attn_offset_10", "offset_output_name": "attn_offset_out_10", "cached_keys_input_name": "attn_cached_keys_10", "cached_keys_output_name": "attn_cached_keys_out_10", "cached_values_input_name": "attn_cached_values_10", "cached_values_output_name": "attn_cached_values_out_10", "cached_positions_input_name": "attn_cached_positions_10", "cached_positions_output_name": "attn_cached_positions_out_10", "offset_shape": [ 1 ], "cache_shape": [ 1, 4, 1600, 64 ], "positions_shape": [ 1, 1600 ], "cache_dtype": "float32", "positions_dtype": "int32" }, { "index": 11, "decoder_index": 7, "layer_index": 3, "context": 1600, "num_heads": 4, "head_dim": 64, "offset_input_name": "attn_offset_11", "offset_output_name": "attn_offset_out_11", "cached_keys_input_name": "attn_cached_keys_11", "cached_keys_output_name": "attn_cached_keys_out_11", "cached_values_input_name": "attn_cached_values_11", "cached_values_output_name": "attn_cached_values_out_11", "cached_positions_input_name": "attn_cached_positions_11", "cached_positions_output_name": "attn_cached_positions_out_11", "offset_shape": [ 1 ], "cache_shape": [ 1, 4, 1600, 64 ], "positions_shape": [ 1, 1600 ], "cache_dtype": "float32", "positions_dtype": "int32" } ] } }