| { | |
| "model_type": "chatterbox_flash_coreml", | |
| "base_model": "ResembleAI/chatterbox-flash", | |
| "source_revision": "4385507288b8197e6dab8b4e6b1603328d549d9d", | |
| "format": "coreml-mlmodelc", | |
| "compute_precision": "fp16", | |
| "parameter_count": 798437191, | |
| "sample_rate": 24000, | |
| "language": ["en"], | |
| "components": { | |
| "t3": { | |
| "path": "t3", | |
| "parameter_count": 532406272, | |
| "text_len": 256, | |
| "block_size": 16, | |
| "max_seq": 1024, | |
| "graphs": [ | |
| "ConditioningEncoder.mlmodelc", | |
| "TextPrefill.mlmodelc", | |
| "BlockDecoder.mlmodelc" | |
| ] | |
| }, | |
| "audio": { | |
| "path": "audio", | |
| "parameter_count": 266030919, | |
| "token_len": 192, | |
| "mel_len": 384, | |
| "meanflow_steps": 2, | |
| "graphs": [ | |
| "FlowSpeakerProjector.mlmodelc", | |
| "FlowEncoder.mlmodelc", | |
| "FlowEstimator.mlmodelc", | |
| "HiFTVocoder.mlmodelc" | |
| ] | |
| } | |
| }, | |
| "capabilities": { | |
| "text_to_speech": true, | |
| "voice_cloning_with_external_reference_conditioning": true, | |
| "fully_coreml_reference_audio_encoding": false | |
| } | |
| } | |