Instructions to use audarai/Audar-ASR-V1-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use audarai/Audar-ASR-V1-Flash with Transformers:

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

pipe = pipeline("automatic-speech-recognition", model="audarai/Audar-ASR-V1-Flash", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("audarai/Audar-ASR-V1-Flash", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("audarai/Audar-ASR-V1-Flash", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use audarai/Audar-ASR-V1-Flash with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf audarai/Audar-ASR-V1-Flash:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf audarai/Audar-ASR-V1-Flash:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf audarai/Audar-ASR-V1-Flash:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf audarai/Audar-ASR-V1-Flash:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf audarai/Audar-ASR-V1-Flash:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf audarai/Audar-ASR-V1-Flash:Q4_K_M

Use Docker

docker model run hf.co/audarai/Audar-ASR-V1-Flash:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use audarai/Audar-ASR-V1-Flash with Ollama:
```
ollama run hf.co/audarai/Audar-ASR-V1-Flash:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use audarai/Audar-ASR-V1-Flash with Docker Model Runner:
```
docker model run hf.co/audarai/Audar-ASR-V1-Flash:Q4_K_M
```

Lemonade

How to use audarai/Audar-ASR-V1-Flash with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull audarai/Audar-ASR-V1-Flash:Q4_K_M

Run and chat with the model

lemonade run user.Audar-ASR-V1-Flash-Q4_K_M

List all available models

lemonade list

Atomic Chat

Dragonhead commited on Jul 7

Commit

3ca2dbd

verified ·

1 Parent(s): bde9fef

Precise parameter counts: exact values verified by loading the actual model (thinker.audio_tower / model / lm_head split)

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -37,7 +37,7 @@ tags:
 ![License](https://img.shields.io/badge/license-AudarAI%20Open%20v1.0-6f42c1)
 ![Task](https://img.shields.io/badge/task-ASR-blue)
 ![Format](https://img.shields.io/badge/format-Transformers%20%2B%20GGUF-blue)
-![Params](https://img.shields.io/badge/decoder-~0.6B-f59e0b)
 ![Languages](https://img.shields.io/badge/languages-30%20(Arabic%20%2B%20English%20%2B%2028)-f59e0b)
 ![Runs on](https://img.shields.io/badge/runs%20on-CPU%20%7C%20GPU%20%7C%20edge-informational)
@@ -75,7 +75,9 @@ the hardest dialectal audio, use the larger **Turbo** tier.
 <tr><td><b>Task</b></td><td>Automatic speech recognition (audio → text)</td></tr>
 <tr><td><b>Approach</b></td><td>Generative ASR — audio encoder + language-model decoder</td></tr>
 <tr><td><b>Training</b></td><td>300k+ hrs dialectal pretraining → dialect-targeted SFT → GRPO alignment</td></tr>
-<tr><td><b>Decoder size</b></td><td>~0.6B (full model ~0.78B, bf16)</td></tr>
 <tr><td><b>Audio input</b></td><td>16 kHz mono; 30 s context (longer audio is chunked/streamed)</td></tr>
 <tr><td><b>Languages</b></td><td>Arabic (MSA + Gulf/Egyptian/Levantine/Maghrebi dialects) + English + 28 more</td></tr>
 <tr><td><b>Runtimes</b></td><td>🤗 Transformers (GPU) · GGUF / llama.cpp (CPU · GPU · edge)</td></tr>

 ![License](https://img.shields.io/badge/license-AudarAI%20Open%20v1.0-6f42c1)
 ![Task](https://img.shields.io/badge/task-ASR-blue)
 ![Format](https://img.shields.io/badge/format-Transformers%20%2B%20GGUF-blue)
+![Params](https://img.shields.io/badge/params-0.78B%20total-f59e0b)
 ![Languages](https://img.shields.io/badge/languages-30%20(Arabic%20%2B%20English%20%2B%2028)-f59e0b)
 ![Runs on](https://img.shields.io/badge/runs%20on-CPU%20%7C%20GPU%20%7C%20edge-informational)
 <tr><td><b>Task</b></td><td>Automatic speech recognition (audio → text)</td></tr>
 <tr><td><b>Approach</b></td><td>Generative ASR — audio encoder + language-model decoder</td></tr>
 <tr><td><b>Training</b></td><td>300k+ hrs dialectal pretraining → dialect-targeted SFT → GRPO alignment</td></tr>
+<tr><td><b>Decoder parameters</b></td><td>596,049,920 (0.60B)</td></tr>
+<tr><td><b>Audio encoder parameters</b></td><td>186,376,192 (0.19B)</td></tr>
+<tr><td><b>Total parameters</b></td><td>782,426,112 (0.78B, bf16)</td></tr>
 <tr><td><b>Audio input</b></td><td>16 kHz mono; 30 s context (longer audio is chunked/streamed)</td></tr>
 <tr><td><b>Languages</b></td><td>Arabic (MSA + Gulf/Egyptian/Levantine/Maghrebi dialects) + English + 28 more</td></tr>
 <tr><td><b>Runtimes</b></td><td>🤗 Transformers (GPU) · GGUF / llama.cpp (CPU · GPU · edge)</td></tr>