te-medium (CTranslate2)
A CTranslate2 conversion of vasista22/whisper-telugu-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 Telugu by SPRING Lab, IIT Madras. 1.5 GB once converted.
Measured in LiveWhisper
| metric | result |
|---|---|
| FLEURS word error | 37.1% (large-v3 74.4%) |
| delivered Telugu romanized | 36.2% (large-v3 71.6%) |
from faster_whisper import WhisperModel
model = WhisperModel("itsskofficial/livewhisper-te-medium", device="cuda", compute_type="int8_float16")
- Downloads last month
- 32
Model tree for itsskofficial/livewhisper-te-medium
Base model
vasista22/whisper-telugu-medium