Downloads · 30 days
509
69% of all-time downloads
whisper-large-v2-formosan-lang-tokens-ct2
ILRDF/whisper-large-v2-formosan-lang-tokens-ct2
whisper-large-v2-formosan-lang-tokens-ct2 is a automatic speech recognition model from ILRDF. Use it when you need speech turned into text. It is set up for faster-whisper. The card lists the license as cc-by-nc-4.0.
This repository contains the CTranslate2 float16 conversion of ILRDF/whisper-large-v2-formosan-lang-tokens.
All-time downloads
735
Public
Repo size
3.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- faster-whisper
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Sep 14, 2026
- Updated
- Sep 14, 2026
- SHA
- fb6a4542
Base models
Spaces
Model card
From the Hugging Face model README
Whisper Large-v2 Formosan Language Tokens (CTranslate2)
This repository contains the CTranslate2 float16 conversion of
ILRDF/whisper-large-v2-formosan-lang-tokens.
The conversion was made with CTranslate2's Transformers converter and keeps
the original tokenizer and preprocessing configuration. It is intended for
use with faster-whisper and WhisperX.
from faster_whisper import WhisperModel
model = WhisperModel(
"ILRDF/whisper-large-v2-formosan-lang-tokens-ct2",
device="cuda",
compute_type="float16",
)
Conversion settings:
- source:
ILRDF/whisper-large-v2-formosan-lang-tokens - quantization:
float16 - converter: CTranslate2
- Task
- Automatic Speech Recognition
- Library
- faster-whisper
- License
- cc-by-nc-4.0
- Created
- Sep 14, 2026
- Updated
- Sep 14, 2026