Downloads · 30 days
4
4% of all-time downloads
whisper-medium-sk-ct2
dongd87/whisper-medium-sk-ct2
whisper-medium-sk-ct2 is a automatic speech recognition model from dongd87. Use it when you need speech turned into text. It is set up for ctranslate2. The card lists the license as mit.
All-time downloads
100
Public
Repo size
769 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin769 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- ctranslate2
- License
- mit
- Access
- Public
- Created
- May 16, 2026
- Updated
- May 16, 2026
- SHA
- 893d4020
Base models
Model card
From the Hugging Face model README
whisper-medium-sk-ct2
CTranslate2 converted Whisper model.
Source model
- Repo:
NaiveNeuron/whisper-medium-sk - Commit:
939a05a6537ba23df0b09650bd53d74a7e76c5ca
Conversion
- Format:
CTranslate2 - Quantization:
int8_float16
Compatible libraries
faster-whisperctranslate2
Notes
This model was converted automatically from the original HuggingFace Transformers format to CTranslate2 format.
The model is intended for use with:
faster-whisperctranslate2
Usage
from faster_whisper import WhisperModel
model = WhisperModel(
"whisper-medium-sk-ct2",
device="cuda",
)
segments, info = model.transcribe("audio.wav")
for segment in segments:
print(segment.text)
- Task
- Automatic Speech Recognition
- Library
- ctranslate2
- License
- mit
- Languages
- sk
- Created
- May 16, 2026
- Updated
- May 16, 2026