Any-to-Any
Transformers
Safetensors
English
Korean
raon
feature-extraction
speech
audio
multimodal
custom_code
Instructions to use KRAFTON/Raon-Speech-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KRAFTON/Raon-Speech-9B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("KRAFTON/Raon-Speech-9B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -198,6 +198,24 @@ curl -X POST http://localhost:8000/v1/audio/speech \
|
|
| 198 |
}' --output cloned.wav
|
| 199 |
```
|
| 200 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 201 |
|
| 202 |
## License
|
| 203 |
|
|
|
|
| 198 |
}' --output cloned.wav
|
| 199 |
```
|
| 200 |
|
| 201 |
+
# 5. Test — STT
|
| 202 |
+
```bash
|
| 203 |
+
curl -X POST http://localhost:8000/v1/chat/completions \
|
| 204 |
+
-H "Content-Type: application/json" \
|
| 205 |
+
-d '{
|
| 206 |
+
"model": "KRAFTON/Raon-Speech-9B",
|
| 207 |
+
"messages": [
|
| 208 |
+
{
|
| 209 |
+
"role": "user",
|
| 210 |
+
"content": [
|
| 211 |
+
{"type": "audio_url", "audio_url": {"url": "data:audio/wav;base64,'"$(base64 -w0 audio.wav)"'"}},
|
| 212 |
+
{"type": "text", "text": "Transcribe the audio into text."}
|
| 213 |
+
]
|
| 214 |
+
}
|
| 215 |
+
]
|
| 216 |
+
}'
|
| 217 |
+
```
|
| 218 |
+
|
| 219 |
|
| 220 |
## License
|
| 221 |
|