| { |
| "model_type": "xy_tokenizer", |
| "auto_map": { |
| "AutoFeatureExtractor": "feature_extraction_xy_tokenizer.XYTokenizerFeatureExtractor", |
| "AutoConfig": "configuration_xy_tokenizer.XYTokenizerConfig", |
| "AutoModel": "modeling_xy_tokenizer.XYTokenizerModel" |
| }, |
| "input_sample_rate": 16000, |
| "output_sample_rate": 24000, |
| "encoder_downsample_rate": 1280, |
| "decoder_upsample_rate": 1920, |
| "code_dim": 3072, |
| "params": { |
| "feature_extractor_kwargs": { |
| "chunk_length": 30, |
| "feature_size": 80, |
| "hop_length": 160, |
| "n_fft": 400, |
| "n_samples": 480000, |
| "nb_max_frames": 3000, |
| "padding_side": "right", |
| "padding_value": 0.0, |
| "sampling_rate": 16000, |
| "return_attention_mask": true, |
| "return_tensors": "pt" |
| }, |
| "semantic_encoder_kwargs": { |
| "num_mel_bins": 80, |
| "sampling_rate": 16000, |
| "hop_length": 160, |
| "stride_size": 2, |
| "kernel_size": 3, |
| "d_model": 768, |
| "scale_embedding": false, |
| "max_audio_seconds": 30, |
| "encoder_layers": 12, |
| "encoder_attention_heads": 12, |
| "encoder_ffn_dim": 3072, |
| "activation_function": "gelu" |
| }, |
| "semantic_encoder_adapter_kwargs": { |
| "input_dim": 768, |
| "output_dim": 768, |
| "d_model": 768, |
| "max_source_positions": 1500, |
| "encoder_layers": 4, |
| "encoder_attention_heads": 12, |
| "encoder_ffn_dim": 3072 |
| }, |
| "acoustic_encoder_kwargs": { |
| "num_mel_bins": 80, |
| "sampling_rate": 16000, |
| "hop_length": 160, |
| "stride_size": 2, |
| "kernel_size": 3, |
| "d_model": 768, |
| "scale_embedding": false, |
| "max_audio_seconds": 30, |
| "encoder_layers": 12, |
| "encoder_attention_heads": 12, |
| "encoder_ffn_dim": 3072, |
| "activation_function": "gelu" |
| }, |
| "pre_rvq_adapter_kwargs": { |
| "input_dim": 1536, |
| "output_dim": 768, |
| "d_model": 768, |
| "max_source_positions": 1500, |
| "encoder_layers": 4, |
| "encoder_attention_heads": 12, |
| "encoder_ffn_dim": 3072 |
| }, |
| "downsample_kwargs": { |
| "d_model": 768, |
| "avg_pooler": 4 |
| }, |
| "quantizer_kwargs": { |
| "input_dim": 3072, |
| "rvq_dim": 512, |
| "output_dim": 3072, |
| "num_quantizers": 8, |
| "codebook_size": 1024, |
| "codebook_dim": 512, |
| "quantizer_dropout": 0.0 |
| }, |
| "post_rvq_adapter_kwargs": { |
| "input_dim": 3072, |
| "output_dim": 3072, |
| "d_model": 768, |
| "max_source_positions": 375, |
| "encoder_layers": 4, |
| "encoder_attention_heads": 12, |
| "encoder_ffn_dim": 3072 |
| }, |
| "upsample_kwargs": { |
| "d_model": 768, |
| "stride": 4 |
| }, |
| "acoustic_decoder_kwargs": { |
| "num_mel_bins": 80, |
| "sampling_rate": 16000, |
| "hop_length": 160, |
| "stride_size": 2, |
| "kernel_size": 3, |
| "d_model": 768, |
| "scale_embedding": false, |
| "max_audio_seconds": 30, |
| "decoder_layers": 12, |
| "decoder_attention_heads": 12, |
| "decoder_ffn_dim": 3072, |
| "activation_function": "gelu" |
| }, |
| "vocos_kwargs": { |
| "input_channels": 80, |
| "dim": 512, |
| "intermediate_dim": 4096, |
| "num_layers": 30, |
| "n_fft": 960, |
| "hop_size": 240, |
| "padding": "same" |
| } |
| }, |
| "torch_dtype": "float32", |
| "transformers_version": "4.51.0" |
| } |
