Instructions to use VohoAI/voho-saudi-speak-0.6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VohoAI/voho-saudi-speak-0.6b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="VohoAI/voho-saudi-speak-0.6b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VohoAI/voho-saudi-speak-0.6b")
model = AutoModelForCausalLM.from_pretrained("VohoAI/voho-saudi-speak-0.6b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use VohoAI/voho-saudi-speak-0.6b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VohoAI/voho-saudi-speak-0.6b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VohoAI/voho-saudi-speak-0.6b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VohoAI/voho-saudi-speak-0.6b

SGLang

How to use VohoAI/voho-saudi-speak-0.6b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "VohoAI/voho-saudi-speak-0.6b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VohoAI/voho-saudi-speak-0.6b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "VohoAI/voho-saudi-speak-0.6b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VohoAI/voho-saudi-speak-0.6b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use VohoAI/voho-saudi-speak-0.6b with Docker Model Runner:
```
docker model run hf.co/VohoAI/voho-saudi-speak-0.6b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Voho Saudi Speak 0.6B

Turns formal Arabic into Arabic the way Saudis actually say it, in Najdi, Hijazi or Khaleeji, from Voho.

A voice agent that reads out written Arabic sounds like a news bulletin. This small model sits between the text and the voice: give it a formal sentence and a dialect, and it returns what a person from Riyadh, Jeddah or the Eastern Province would say on a phone call. It is 0.6B parameters, small enough to run on a CPU or next to a speech model on one GPU.

Results

chrF++ against what a Saudi speaker actually said, on 1,000 held-out sentences (higher is better):

Dialect	Sentences	Formal text unchanged	Qwen3-0.6B, untrained	Voho Saudi Speak 0.6B	Gemini 2.5 Flash
All test sentences	1,000	61.8	52.2	75.7	68.7
Najdi (Riyadh, central)	462	62.2	51.5	77.0	70.6
Hijazi (Jeddah, Makkah)	257	65.8	57.7	75.8	69.1
Khaleeji (Eastern Province)	281	56.6	47.3	73.2	64.7

"Formal text unchanged" is the floor: dialect and formal Arabic share most of their letters, so leaving the sentence as it is already scores well. Gemini 2.5 Flash is a much larger model doing the same job with the same instruction, shown for scale. Read the comparison with care: this model was trained on SADA and learned its spelling and phrasing, which Gemini never saw, and the formal inputs were themselves written by Gemini. On this test set that favours the small model; it does not mean a 0.6B model is better at Saudi Arabic than Gemini in general.

Examples

Dialect	Formal input	Voho Saudi Speak 0.6B
Khaleeji	الآن فقط فهمت قصدك وسر اهتمامك.	الحين بس فهمت قصدك وسر اهتمامك.
Najdi	والله لست أرى أي شيء، أقسم بالله، نعم نعم ارفعها أكثر قليلا.	والله ماني شايف أي شيء أقسم بالله إيه إيه أرفعها شوي أكثر
Hijazi	ما هي همومك يا شوماخر؟	إيش همومك يا شوماخر؟

Sentences it never saw in training, from a bank or a clinic line:

Dialect	Formal input	Voho Saudi Speak 0.6B
Najdi	أين أنت الآن؟ أريد أن أحجز موعداً غداً.	وينك الحين أبغى أحجز موعد بكرة
Najdi	لا أستطيع رفع الحد إلى أكثر من ألف ريال، يجب أن تزور الفرع.	ما أقدر أرفع الحد إلى أكثر من ألف ريال لازم تزور الفرع.
Hijazi	سنرسل لك رمز التحقق الآن، من فضلك أخبرني به.	بنرسلك رمز التحقق دحين من فضلك خبرني فيه
Najdi	رقم طلبك هو 48213 وسيصل خلال ثلاثة أيام.	رقم طلبك هو 48213 وبيوصل خلال ثلاث أيام.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "VohoAI/voho-saudi-speak-0.6b"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo)

DIALECT = {"najdi": "النجدية", "hijazi": "الحجازية", "khaleeji": "الخليجية الشرقية"}

def saudi(text, dialect="najdi"):
    prompt = f"أعد صياغة هذه الجملة باللهجة السعودية {DIALECT[dialect]} كما يقولها شخص في مكالمة، بدون أي شرح:\n{text}"
    ids = tok.apply_chat_template([{"role": "user", "content": prompt}], add_generation_prompt=True,
                                  enable_thinking=False, return_tensors="pt")
    out = model.generate(ids, max_new_tokens=96, do_sample=False)
    return tok.decode(out[0, ids.shape[1]:], skip_special_tokens=True).strip()

print(saudi("أين أنت الآن؟ أريد أن أحجز موعداً غداً."))

Training

Base model: Qwen/Qwen3-0.6B (Apache 2.0), full fine-tune, 2 epochs, one NVIDIA L4
Targets: real Saudi speech. 84,394 transcribed sentences from SADA (Najdi, Hijazi and Khaleeji speakers), cleaned of noise transcriptions, repeats and duplicates
Inputs: a formal Modern Standard Arabic version of each sentence, written by Gemini 2.5 Flash from the Saudi original. Pairs where Gemini changed nothing were dropped
Test set: SADA's own test split, never seen in training

Licence and intended use

Non-commercial. SADA is licensed CC BY-NC-SA 4.0, so this model is released under the same licence: research and non-commercial use, with attribution, under the same terms.

For production Saudi Arabic voice, use the Voho API or the LiveKit plugin.

Limitations

Trained on television speech: it knows how Saudis talk in dramas and interviews better than how they talk to a bank.
Its inputs were written by another model, so it learns to undo that model's style of formal Arabic best.
Small model: it can drop or change details in long or complicated sentences, and occasionally swaps who does what ("هل تريد أن أحولك" came out as "تبي تحولك"). Check anything customer-facing.
Writes without diacritics.

Citation

Please cite SADA when using this model:

Saudi Audio Dataset for Arabic (SADA), Saudi Data and AI Authority (SDAIA), 2022.

Downloads last month: 207

Safetensors

Model size

0.6B params

Tensor type

BF16

Model tree for VohoAI/voho-saudi-speak-0.6b

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

(1267)

this model

Quantizations

3 models

VohoAI
/

voho-saudi-speak-0.6b