SYSTRAN/faster-whisper
Faster Whisper transcription with CTranslate2
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
No releases in the last 90 days; the most recent was 368 days ago, with 51 contributors on GitHub.
Gained 19% fewer stars in the last 90 days than in the 90 days before.
Use Cases & Benefits
- Implements a faster, memory-efficient transcription of OpenAI's Whisper speech-to-text model using the CTranslate2 inference engine.
- Delivers up to 4x faster transcription speed than the original Whisper implementation while maintaining comparable accuracy and lower memory usage.
- Use for real-time or batch transcription of audio files on GPU or CPU with support for 8-bit quantization to optimize performance and resource consumption.
- Use for integrating speech recognition into Python applications without requiring external FFmpeg installation, leveraging PyAV for audio decoding.
- Use for generating word-level timestamps and applying voice activity detection filters to improve transcription quality and silence removal.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
- Contributing guide: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models.
This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
2.2K+191
Open issues
19-295
Compared with peers in Deep Learning
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| rohitg00/ai-engineering-from-scratch | 78.3K | +1.6K | 75 | 1 day ago |
| SYSTRAN/faster-whisper | 26.5K | — | 40 | 368 days ago |
| GeeeekExplorer/nano-vllm | 16.3K | — | 12 | — |
| Lightning-AI/litgpt | 13.8K | — | 58 | 129 days ago |
| data-privacy-stack/presidio | 11.8K | — | 64 | 10 days ago |
| opengeos/segment-geospatial | 4.2K | — | 49 | 72 days ago |
| Category median | 13.8K | — | 58 | — |
Discover Repositories
Search across tracked repositories by name or description