Downloads · 30 days
23
19% of all-time downloads
digiphyte/fluister-large-v3
fluister-large-v3 is a automatic speech recognition model from digiphyte. Use it when you need speech turned into text. It is set up for ctranslate2. The card lists the license as mit.
Fluister is an Afrikaans-optimised Whisper. ("Fluister" is Afrikaans for "to whisper".) It is a fine-tune of OpenAI Whisper (openai/whisper-large-v3), merged into the base weights and converted to CTranslate2 (int8) f…
Downloads · 30 days
23
19% of all-time downloads
All-time downloads
121
Public
Repo size
1.6 GB
Likes
1
Public
Click a slice to open those files.
.bin1.6 GB · 100%
From the Hugging Face model README
Fluister is an Afrikaans-optimised Whisper. ("Fluister" is Afrikaans for "to whisper".) It is a fine-tune of OpenAI Whisper (openai/whisper-large-v3), merged into the base weights and converted to CTranslate2 (int8) for use with faster-whisper. By DigiPhyte (Pty) Ltd, South Africa.
On real South African Afrikaans and Afrikaans/English code-switched audio it produces clean Afrikaans where stock Whisper drifts to Dutch spellings ("gebou" not "gebouw", "mense" not "mensen", "eintlik" not "eindelijk"), while keeping English code-switching intact.
from faster_whisper import WhisperModel
model = WhisperModel("digiphyte/fluister-large-v3", device="cuda", compute_type="int8_float16") # CPU: device="cpu", compute_type="int8"
segments, info = model.transcribe("audio.wav", language="af", beam_size=5)
for s in segments:
print(s.text)
Pass language="af"; the Fluister models are tuned for Afrikaans and SA English and should be told
the language rather than relying on auto-detect.
MIT (see LICENSE). This is a derivative work; the base model (OpenAI Whisper, Apache-2.0) and the training data (andreoosthuizen/afrikaans-30s, CC-BY-4.0), plus the LoRA adapter this model reuses (andreoosthuizen/whisper-large-v3-afrikaans, MIT), are credited in NOTICE.