Upload optimized int8 whisper turbo model
Browse files
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- automatic-speech-recognition
|
| 4 |
+
- whisper
|
| 5 |
+
- ctranslate2
|
| 6 |
+
- faster-whisper
|
| 7 |
+
- audio
|
| 8 |
+
language:
|
| 9 |
+
- hu
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# whisper-large-v3-turbo-hu-ct2-int8
|
| 13 |
+
|
| 14 |
+
This is a CTranslate2 / faster-whisper converted version of `openai/whisper-large-v3-turbo` quantized to `int8`. Optimized for fast CPU inference.
|