FlashSR

Esta página da Soniqo documenta FlashSR 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	FlashSR
Papel	Audio super-resolution for low-bandwidth or lossy audio
Backend	MLX int4 default; int8 available
Saída	48 kHz mono waveform, same length as input
Idiomas	Audio-content agnostic
Licença	MIT
Status	Ready through speech upsample and the FlashSR Swift product
Fonte	FlashSR / AudioSR distillation
Produto Swift	`FlashSR`
CLI / runtime	`speech upsample`

Uso

O trecho abaixo reflete a API ou comando atual exposto por speech-swift.

# Upsample a low-bandwidth recording to 48 kHz mono.
.build/release/speech upsample noisy_lowres.wav \
  --variant int4 \
  -o clean_hr.wav

Links do modelo

Notas de implementação

Download requests the single model.safetensors bundle and config explicitly; this is simple enough that byte-weighting is less critical than for sharded models.
Input is resampled to 48 kHz mono and processed in non-overlapping 5.12 second windows.
INT4 is a download-size optimization; runtime weights dequantize to FP, so memory footprint matches int8.
The model conforms to SpeechEnhancementModel, but its semantics are super-resolution rather than denoising.