Faster-Whisper
SYSTRAN
Faster-Whisper reimplements Whisper inference with CTranslate2, offering CPU/GPU quantization, batch transcription and optional word timestamps.
- Rating
- 4.7★
- Pricing
- Free
Editorial verdict
Evaluate it with your chosen model, decoding settings and hardware before setting throughput or cost targets.
Strengths
- Configurable precision and batching
- Word timestamps and VAD within the library
Key features
- CPU/GPU quantized inference
- Batched transcription and word timestamps
- Silero VAD filter and local model loading
Best for
- Batch transcription pipelines
- ASR backends with local model control