Update README.md
Browse files
README.md
CHANGED
|
@@ -10,4 +10,20 @@ pinned: false
|
|
| 10 |
license: mit
|
| 11 |
---
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
| 10 |
license: mit
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# Distil-Whisper + OpenVINO ASR
|
| 14 |
+
|
| 15 |
+
This Hugging Face Space uses Intel's OpenVINO acceleration with HuggingFace's Distil-Whisper model for fast and efficient automatic speech recognition (ASR).
|
| 16 |
+
|
| 17 |
+
## Technologies Used
|
| 18 |
+
- [Distil-Whisper](https://huggingface.co/distil-whisper/distil-large-v2)
|
| 19 |
+
- OpenVINO via HuggingFace Optimum
|
| 20 |
+
- Gradio Interface
|
| 21 |
+
- SoundFile for audio processing
|
| 22 |
+
|
| 23 |
+
## Try it
|
| 24 |
+
Upload an audio file and watch it get transcribed blazingly fast using Intel-optimized Whisper!
|
| 25 |
+
|
| 26 |
+
## Credits
|
| 27 |
+
Built by Khushi Rajurkar on an Intel AI PC environment.
|
| 28 |
+
|
| 29 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|