Distil Whisper
Distil Whisper is a distilled version of OpenAI's Whisper speech recognition model, roughly six times faster and half the size while staying within one percent word error rate of the original on out-of-distribution audio. Released under the MIT licence, it is built for real-time local transcription on consumer hardware and on-device deployment.
- Type
- Multimodal
- Weights
- Closed
- Downloads
- 37
- Likes
- 2
- Pipeline
- automatic speech recognition
- License
- mit
Model hub
OpenVINO/distil-whisper-large-v2-int8-ov
- Repo
- OpenVINO/distil-whisper-large-v2-int8-ov
- Library
- transformers
- Access
- Public
Technical tags and languages
More from Hugging Face
7
-
1.2k DL
Carbon-8B
Text
Carbon-8B is an open-source 8B generative DNA foundation model for DNA/RNA sequence generation, scoring, and…
-
918 DL
nanowhale
Text
nanowhale is a miniature DeepSeek-V4-style language model project, built to reproduce the core DeepSeek-V4 ar…
-
SmolLM2
Text
SmolLM2 is a family of very small open language models at 135M, 360M and 1.7B parameters, trained on 11 trill…
-
SmolLM3
Text
SmolLM3 is a 3B open model with dual-mode reasoning: the same weights answer directly or produce an extended…
About Hugging Face
1
Hugging Face is an Artificial Intelligence company that specializes in Machine Learning, Natural Language Processing, and AI Chatbots.