Model family
Whisper Models
Whisper models are used for ASR, transcription, subtitles, podcast processing, meeting notes, and multilingual audio.
Best for
Audio
Use this family hub to compare Whisper variants for audio workflows, then open the detail page for deeper deployment notes.
Transcription
Use this family hub to compare Whisper variants for transcription workflows, then open the detail page for deeper deployment notes.
Speech recognition
Use this family hub to compare Whisper variants for speech recognition workflows, then open the detail page for deeper deployment notes.
Local
Use this family hub to compare Whisper variants for local workflows, then open the detail page for deeper deployment notes.
Variants
Whisper models grouped by workflow
Audio
Whisper Large V3
OpenAI · Whisper
Best for: Builders adding local transcription, podcast processing, meeting notes, or audio translation.
Local: Commonly used for local transcription workflows; GPU improves batch throughput.
Whisper Large V3 Turbo
OpenAI · Whisper
Best for: Fast transcription and multilingual audio workflows
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Whisper Large V2
OpenAI · Whisper
Best for: Accuracy-focused transcription baseline
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Whisper Medium
OpenAI · Whisper
Best for: Balanced transcription workflows
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Whisper Small
OpenAI · Whisper
Best for: Local transcription with lighter resource needs
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Whisper Base
OpenAI · Whisper
Best for: CPU-friendly transcription experiments
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Whisper Tiny
OpenAI · Whisper
Best for: Very lightweight transcription tests
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Distil-Whisper Large V3
Hugging Face / community · Whisper
Best for: Distilled transcription workflows
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Faster-Whisper Large V3
SYSTRAN / community · Whisper
Best for: Optimized runtime transcription workflows
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Compare
All Whisper models in the directory
| Model | Type | Best for | Local runner notes | License | Detail |
|---|---|---|---|---|---|
| Whisper Large V3 | Audio | Builders adding local transcription, podcast processing, meeting notes, or audio translation. | Commonly used for local transcription workflows; GPU improves batch throughput. | MIT | Open |
| Whisper Large V3 Turbo | Audio | Fast transcription and multilingual audio workflows | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Whisper Large V2 | Audio | Accuracy-focused transcription baseline | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Whisper Medium | Audio | Balanced transcription workflows | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Whisper Small | Audio | Local transcription with lighter resource needs | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Whisper Base | Audio | CPU-friendly transcription experiments | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Whisper Tiny | Audio | Very lightweight transcription tests | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Distil-Whisper Large V3 | Audio | Distilled transcription workflows | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| Faster-Whisper Large V3 | Audio | Optimized runtime transcription workflows | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |