| { | |
| "model": { | |
| "name": "F5TTS_v1_Base", | |
| "tokenizer": "char", | |
| "tokenizer_path": null, | |
| "backbone": "DiT", | |
| "arch": { | |
| "dim": 1024, | |
| "depth": 22, | |
| "heads": 16, | |
| "ff_mult": 2, | |
| "text_dim": 512, | |
| "text_mask_padding": true, | |
| "qk_norm": null, | |
| "conv_layers": 4, | |
| "pe_attn_head": null, | |
| "attn_backend": "torch", | |
| "attn_mask_enabled": false, | |
| "checkpoint_activations": false | |
| }, | |
| "mel_spec": { | |
| "target_sample_rate": 24000, | |
| "n_mel_channels": 100, | |
| "hop_length": 256, | |
| "win_length": 1024, | |
| "n_fft": 1024, | |
| "mel_spec_type": "vocos" | |
| }, | |
| "vocoder": { | |
| "is_local": false, | |
| "local_path": null | |
| } | |
| } | |
| } |