Downloads · 30 days
136
51% of all-time downloads
hurricup/whisper-large-v3-turbo-armenian-ct2
whisper-large-v3-turbo-armenian-ct2 is a automatic speech recognition model from hurricup. Use it when you need speech turned into text. It is set up for ctranslate2. The card lists the license as apache-2.0.
CTranslate2 conversion (float16) of Chillarmo/whisper-large-v3-turbo-armenian, for use with faster-whisper.
Downloads · 30 days
136
51% of all-time downloads
All-time downloads
268
Public
Repo size
1.6 GB
Likes
0
Public
Click a slice to open those files.
.bin1.6 GB · 100%
From the Hugging Face model README
CTranslate2 conversion (float16) of Chillarmo/whisper-large-v3-turbo-armenian, for use with faster-whisper.
This is a derivative produced only by format conversion (no retraining):
ct2-transformers-converter --quantization float16. All credit for the model goes
to the original authors.
from faster_whisper import WhisperModel
model = WhisperModel("hurricup/whisper-large-v3-turbo-armenian-ct2", device="cuda", compute_type="float16")
segments, _ = model.transcribe("audio.wav", language="hy")
print("".join(s.text for s in segments))