automatic speech recognition
Qwen3-ASR-0.6B
by Qwen
license: apache-2.0
714,152 downloads396 likes
Get API KeyAPI Usage
Endpoint
POST https://api.gpu.fm/v1/inferenceRequest
curl -X POST https://api.gpu.fm/v1/inference \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen/Qwen3-ASR-0.6B",
"inputs": [base64 encoded audio],
"parameters": {
"max_new_tokens": 256
}
}'Response
{
"result": {"text": "Hello, how are you today?"},
"usage": {
"inputTokens": 12,
"outputTokens": 128
},
"pricing": {
"total": "0.000018"
}
}Python SDK
import requests
response = requests.post(
"https://api.gpu.fm/v1/inference",
headers={"Authorization": "Bearer YOUR_API_KEY"},
json={
"model": "Qwen/Qwen3-ASR-0.6B",
"inputs": [base64 encoded audio],
"parameters": {"max_new_tokens": 256}
}
)
result = response.json()
print(result["result"])Model Documentation
Full documentation available on HuggingFace →
Pricing
Audio$0.0008/minute
Billed from your prepaid credits. No minimum commitment.
Details
- Model ID
- Qwen/Qwen3-ASR-0.6B
- Pipeline
- automatic speech recognition
- Updated
- 1/30/2026
Tags
safetensorsqwen3_asrautomatic-speech-recognitionarxiv:2601.21337license:apache-2.0eval-resultsdeploy:azureregion:us