| { |
| "activation_function": "gelu_new", |
| "architectures": [ |
| "XttsGPT" |
| ], |
| "attn_pdrop": 0.1, |
| "audio_config": { |
| "mel_channels": 80, |
| "output_sample_rate": 24000, |
| "sample_rate": 22050 |
| }, |
| "auto_map": { |
| "AutoConfig": "AstraMindAI/xtts2-gpt--gpt_config.XTTSGPTConfig", |
| "AutoModelForCausalLM": "AstraMindAI/xtts2-gpt--xtts2_gpt_modeling.XttsGPT", |
| "AutoTokenizer": "AstraMindAI/xtts2-gpt--tokenizer.XTTSTokenizerFast" |
| }, |
| "decoder_input_dim": 1024, |
| "enable_redaction": false, |
| "gpt_batch_size": 1, |
| "gpt_max_audio_tokens": 605, |
| "hidden_size": 1024, |
| "initializer_range": 0.02, |
| "kv_cache": true, |
| "layer_norm_epsilon": 1e-05, |
| "max_audio_tokens": 605, |
| "max_prompt_tokens": 70, |
| "max_text_tokens": 402, |
| "model_type": "xtts_gpt", |
| "n_inner": 4096, |
| "num_attention_heads": 16, |
| "num_audio_tokens": 1026, |
| "num_hidden_layers": 30, |
| "number_text_tokens": 6681, |
| "reorder_and_upcast_attn": false, |
| "scale_attn_by_inverse_layer_idx": false, |
| "start_audio_token": 1024, |
| "start_text_token": null, |
| "stop_audio_token": 1025, |
| "stop_text_token": null, |
| "transformers_version": "4.46.0", |
| "use_masking_gt_prompt_approach": true, |
| "use_perceiver_resampler": true, |
| "vocab_size": 6681 |
| } |
|
|
