Downloads · 30 days
36
32% of all-time downloads
ISTNetworks/ultravox-v0_6-qwen-3-32b-arabic
ultravox-v0_6-qwen-3-32b-arabic is a audio-text-to-text model from ISTNetworks. Use it for the audio-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
fixie-ai/ultravox-v06-qwen-3-32b with its Whisper audio tower adapted for dialectal Arabic using oddadmix/whisper-large-v3-turbo-arabic-dialectal-v2.
Downloads · 30 days
36
32% of all-time downloads
All-time downloads
113
Public
Parameters
33.5B
66.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors66.9 GB · 100%
From the Hugging Face model README
fixie-ai/ultravox-v0_6-qwen-3-32b with its Whisper
audio tower adapted for dialectal Arabic using
oddadmix/whisper-large-v3-turbo-arabic-dialectal-v2.
This repository is self-contained: the Qwen3-32B language model, the merged audio tower, the multimodal projector, the tokenizer and the Whisper feature extractor all ship here, so no other repo is fetched at load time.
| Component | Source |
|---|---|
language_model.* | Qwen/Qwen3-32B (bf16, 64 layers) |
audio_tower.* | delta merge described above (Whisper-large-v3-turbo encoder, 32 layers) |
multi_modal_projector.* | fixie-ai/ultravox-v0_6-qwen-3-32b (finetuned) |
| tokenizer / chat template | fixie-ai/ultravox-v0_6-qwen-3-32b (Qwen3) |
audio_processor/ | openai/whisper-large-v3-turbo feature extractor |
import librosa, torch, transformers
repo = "ISTNetworks/ultravox-v0_6-qwen-3-32b-arabic"
processor = transformers.AutoProcessor.from_pretrained(repo, trust_remote_code=True)
model = transformers.AutoModel.from_pretrained(
repo, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map="auto"
)
audio, sr = librosa.load("sample.wav", sr=16000)
turns = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "استمع للصوت وأجب باللغة العربية.\n<|audio|>"},
]
text = processor.tokenizer.apply_chat_template(
turns, add_generation_prompt=True, tokenize=False, enable_thinking=False
)
inputs = processor(text=text, audio=audio, sampling_rate=sr, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=128)
print(processor.tokenizer.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
Audio is inserted with the <|audio|> placeholder in the user turn. Inference needs ~67 GB of bf16 weights
(2×80 GB GPUs, or one 80 GB GPU with quantization / CPU offload).