| { |
| "architectures": [ |
| "SpeechModel" |
| ], |
| "audio_configuration": { |
| "acoustic_model_config": { |
| "codebook_dim": 8, |
| "codebook_loss_weight": 1.0, |
| "codebook_size": 1024, |
| "commitment_loss_weight": 0.25, |
| "decoder_hidden_size": 1024, |
| "downsampling_ratios": [ |
| 8, |
| 5, |
| 4, |
| 2, |
| 3 |
| ], |
| "encoder_hidden_size": 64, |
| "hidden_size": 256, |
| "hop_length": 960, |
| "model_type": "dac", |
| "n_codebooks": 9, |
| "quantizer_dropout": 0, |
| "sampling_rate": 16000, |
| "upsampling_ratios": [ |
| 8, |
| 5, |
| 4, |
| 2, |
| 3 |
| ] |
| }, |
| "architectures": [ |
| "HiggsAudioV2TokenizerModel" |
| ], |
| "block_dilations": [ |
| 1, |
| 1 |
| ], |
| "channel_ratios": [ |
| 1, |
| 1 |
| ], |
| "codebook_dim": 64, |
| "codebook_size": 1024, |
| "downsample_factor": 320, |
| "dtype": "float32", |
| "initializer_range": 0.02, |
| "kernel_size": 3, |
| "model_type": "higgs_audio_v2_tokenizer", |
| "sample_rate": 24000, |
| "semantic_model_config": { |
| "activation_dropout": 0.1, |
| "apply_spec_augment": true, |
| "attention_dropout": 0.1, |
| "bos_token_id": 1, |
| "classifier_proj_size": 256, |
| "conv_bias": false, |
| "conv_dim": [ |
| 512, |
| 512, |
| 512, |
| 512, |
| 512, |
| 512, |
| 512 |
| ], |
| "conv_kernel": [ |
| 10, |
| 3, |
| 3, |
| 3, |
| 3, |
| 2, |
| 2 |
| ], |
| "conv_pos_batch_norm": false, |
| "conv_stride": [ |
| 5, |
| 2, |
| 2, |
| 2, |
| 2, |
| 2, |
| 2 |
| ], |
| "ctc_loss_reduction": "sum", |
| "ctc_zero_infinity": false, |
| "do_stable_layer_norm": false, |
| "eos_token_id": 2, |
| "feat_extract_activation": "gelu", |
| "feat_extract_norm": "group", |
| "feat_proj_dropout": 0.0, |
| "feat_proj_layer_norm": true, |
| "final_dropout": 0.1, |
| "hidden_act": "gelu", |
| "hidden_dropout": 0.1, |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "layer_norm_eps": 1e-05, |
| "layerdrop": 0.1, |
| "mask_feature_length": 10, |
| "mask_feature_min_masks": 0, |
| "mask_feature_prob": 0.0, |
| "mask_time_length": 10, |
| "mask_time_min_masks": 2, |
| "mask_time_prob": 0.0, |
| "model_type": "hubert", |
| "num_attention_heads": 12, |
| "num_conv_pos_embedding_groups": 16, |
| "num_conv_pos_embeddings": 128, |
| "num_feat_extract_layers": 7, |
| "num_hidden_layers": 12, |
| "pad_token_id": 0, |
| "use_weighted_layer_sum": false, |
| "vocab_size": 32 |
| }, |
| "semantic_sample_rate": 16000, |
| "strides": [ |
| 1, |
| 1 |
| ], |
| "target_bandwidths": [ |
| 0.5, |
| 1, |
| 1.5, |
| 2 |
| ], |
| "transformers_version": "5.3.0.dev0", |
| "unit_kernel_size": 3 |
| }, |
| "auto_map": { |
| "AutoConfig": "modeling_speech.SpeechConfig", |
| "AutoModel": "modeling_speech.SpeechModel", |
| "AutoModelForTextToWaveform": "modeling_speech.SpeechModel" |
| }, |
| "checkpoint_sha256": "e2e093e8323a4504c1d482b39c0ffbef143553f584bd524eea2c8536b768d861", |
| "dtype": "bfloat16", |
| "geometry": { |
| "head_dim": 128, |
| "heads": 32, |
| "hidden_size": 2560, |
| "intermediate_size": 9728, |
| "kv_heads": 8, |
| "layers": 36, |
| "rms_epsilon": 1e-06, |
| "rope_theta": 1000000.0, |
| "text_vocabulary": 151936 |
| }, |
| "inference": { |
| "version": 1, |
| "sampling": { |
| "temperature": 0.8, |
| "top_p": 0.8, |
| "top_k": 30, |
| "max_new_positions": 1500, |
| "seed": 20261102 |
| }, |
| "decoding": { |
| "alignment_strength": 0, |
| "plausible_tokens": 25, |
| "recover_loops": true |
| }, |
| "adapter_multiplier": 1 |
| }, |
| "model_type": "agbalu_speech", |
| "sampling_rate": 24000, |
| "source_stamp": { |
| "config_hash": "11c975e42f84cde0d25d1bb162ae5934f3e49a755fb0da95e93e60eb7f5660cd", |
| "dirty": true, |
| "git_sha": "4c0e119b42518dafee8be80d10d8dfdb13090295", |
| "version": 1, |
| "version_tag": null |
| }, |
| "transformers_version": "5.17.0" |
| } |
|
|
