| { | |
| "text_format": "bpe", | |
| "vocab_size": 8192, | |
| "num_codebooks": 16, | |
| "codebook_size": 1024, | |
| "d_model": 768, | |
| "n_heads": 12, | |
| "n_layers": 9, | |
| "n_voice_queries": 10, | |
| "special_tokens": { | |
| "<pad>": 0, | |
| "<bos>": 1, | |
| "<eot>": 2, | |
| "<soa>": 3, | |
| "<slot>": 4, | |
| "<eoa>": 5, | |
| "<en>": 6, | |
| "<vi>": 7 | |
| }, | |
| "sample_rate": 48000, | |
| "codec_frame_rate": 12.5 | |
| } |