Whisper Large-v3 Turbo

Esta página da Soniqo documenta Whisper Large-v3 Turbo 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	Whisper Large-v3 Turbo
Papel	General multilingual speech-to-text
Backend	CoreML fp16 on CPU and Neural Engine
Saída	Text transcript
Idiomas	Whisper multilingual set, about 100 languages
Licença	MIT weights from OpenAI
Status	Ready through speech transcribe --engine whisper and the WhisperASR Swift product
Fonte	openai/whisper-large-v3-turbo
Produto Swift	`WhisperASR`
CLI / runtime	`speech transcribe --engine whisper`

Uso

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

# Transcribe with the native CoreML Whisper runtime.
.build/release/speech transcribe recording.wav --engine whisper
.build/release/speech transcribe recording.wav --engine whisper --language en

Links do modelo

Notas de implementação

LibriSpeech test-clean slice on an M5 Pro: 1.40% WER, mean RTF 0.089, 6.1 s model load, 384 MB peak RSS — versus 1.53% / 0.085 / 100.2 s / 507 MB for a direct WhisperKit run of the same model.
The bundle splits into four CoreML models — mel spectrogram, audio encoder, decoder context prefill, and a KV-cached text decoder — with the encoder and decoder on the Neural Engine.
Greedy no-timestamp decoding with automatic language detection or a --language hint; audio is processed in 30 s chunks with a repeated-word guard against greedy hallucination loops.
Word timestamps, temperature fallback, and VAD-guided long-form seeking are not implemented yet; --model accepts turbo, large-v3-turbo, or any Hugging Face repo ID.