Downloads · 30 days
14
61% of all-time downloads
livewhisper-ta-medium
itsskofficial/livewhisper-ta-medium
livewhisper-ta-medium is a automatic speech recognition model from itsskofficial. Use it when you need speech turned into text. It is set up for ctranslate2. The card lists the license as apache-2.0.
A CTranslate2 conversion of vasista22/whisper-tamil-medium for faster-whisper, as downloaded by LiveWhisper, a voice dictation app for Windows.
All-time downloads
23
Public
Repo size
1.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.5 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- ctranslate2
- License
- apache-2.0
- Access
- Public
- Created
- Sep 21, 2026
- Updated
- Sep 21, 2026
- SHA
- 97467835
Base models
Model card
From the Hugging Face model README
ta-medium (CTranslate2)
A CTranslate2 conversion of vasista22/whisper-tamil-medium for faster-whisper, as downloaded by LiveWhisper, a voice dictation app for Windows.
All credit for the model goes to its original authors. This repository only
changes the file format (float16 weights, plus tokenizer.json and
preprocessor_config.json that faster-whisper needs). The licence is the
original's: apache-2.0.
Whisper-medium fine-tuned on Tamil by SPRING Lab, IIT Madras. 1.5 GB once converted.
Measured in LiveWhisper
| metric | result |
|---|---|
| FLEURS word error | 23.2% (large-v3 56.9%) |
| delivered Tanglish | 22.4% (large-v3 51.8%) |
from faster_whisper import WhisperModel
model = WhisperModel("itsskofficial/livewhisper-ta-medium", device="cuda", compute_type="int8_float16")
- Task
- Automatic Speech Recognition
- Library
- ctranslate2
- License
- apache-2.0
- Languages
- ta
- Created
- Sep 21, 2026
- Updated
- Sep 21, 2026