Fish Audio S2 Pro
Esta página da Soniqo documenta Fish Audio S2 Pro conforme a implementação local em speech-swift / speech-core. Os links do Hugging Face ficam abaixo das notas de integração.
Página interna primeiro
Cards e menus apontam primeiro para cá; os links do modelo fonte e dos bundles continuam disponíveis nesta página.
Visão geral
| Modelo | Fish Audio S2 Pro |
|---|---|
| Papel | Experimental multilingual TTS with raw-reference cloning and style markers |
| Backend | MLX fp16 |
| Saída | 44.1 kHz mono PCM |
| Idiomas | Multilingual |
| Licença | Research / non-commercial bundle; obtain Fish Audio license for commercial exposure |
| Status | Programmatic runtime; CLI integration is still pending |
| Fonte | Fish Audio S2 Pro |
| Produto Swift | FishAudioTTS |
| CLI / runtime | Programmatic runtime today; planned speech speak --engine fish-audio |
Uso
O trecho abaixo reflete a API ou comando atual exposto por speech-swift.
import FishAudioTTS
let model = try await FishAudioTTSModel.fromPretrained()
let pcm = try await model.generate(
text: "आज मैं बहुत खुश हूँ। [excited]",
referenceAudioURL: URL(fileURLWithPath: "reference.wav"),
referenceText: "नमस्ते, यह संदर्भ आवाज है।"
)Links do modelo
Notas de implementação
- Download uses the newer explicit byte-weighted file manifest, so progress reflects real transferred bytes across the multi-GB shards.
- Control markers include [pause], [emphasis], [laughing], [excited], [angry], [whisper], [screaming], [shouting], [surprised], and [sad].
- The runtime generates 10 DAC codebook rows, then decodes generated or reference-conditioned codebooks through FishAudioCodec.
- Current tests cover bundle loading, codebook generation, codec encode/decode, Hindi cloning, and ASR round-trip gates.