Model reference · open weights

Whisper-tunisian-codeswitch

Available as managed deployment Audio oddadmix · community Speech→text 1 variants 673 dl/mo

Whisper-tunisian-codeswitch is an open-weight audio or speech model from oddadmix. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byoddadmix
TypeAudio & music
TaskSpeech→text
Parameters (lead)1.5B
Based onoddadmix/whisper-large-v3-tunisian-codeswitch-asr-v2
Released2026-07-28
Popularity673 downloads / month
LicenceUnknown

About

What Whisper-tunisian-codeswitch is

Whisper-large-v3 full fine-tune for Tunisian Arabic ↔ French/English code-switched ASR (NADI 2026 shared task, subtask 1.3).

Read the full model card
  • Recipe: fresh full-FT from tun-asr-aug-v4 on FARUKxAUTO/tunisian-asr-cleaned (46K, dense Tunisian↔French code-switch) + NADI TEDx train replay, 2 epochs, --spec_augment, paged_adamw_8bit, lr 5e-6 (a single longer cosine schedule — 2 epochs is the sweet spot).
  • Results: validation WER 17.26% / CER 6.91%; blind test WER 15.22 (🥉).
  • Decode greedy, language="ar", task="transcribe". Submit raw (scorer applies clean_transcription).
from transformers import WhisperForConditionalGeneration, WhisperProcessor
import torch
m = WhisperForConditionalGeneration.from_pretrained("oddadmix/nadi2026-subtask1.3-tunisian-codeswitch-asr-faruk-v7", torch_dtype=torch.bfloat16).cuda().eval()
p = WhisperProcessor.from_pretrained("oddadmix/nadi2026-subtask1.3-tunisian-codeswitch-asr-faruk-v7")
# feats = p(audio, sampling_rate=16000, return_tensors="pt").input_features.cuda().to(torch.bfloat16)
# ids = m.generate(feats, language="ar", task="transcribe", max_new_tokens=256)
# print(p.batch_decode(ids, skip_special_tokens=True))

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys whisper-tunisian-codeswitch for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (whisper-tunisian-codeswitch below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="whisper-tunisian-codeswitch" -F file=@audio.mp3

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms