Any-to-Any
Transformers
Safetensors
English
Korean
raon
feature-extraction
speech
audio
multimodal
mixture-of-experts
text-to-speech
automatic-speech-recognition
custom_code
Instructions to use KRAFTON/A.X-K2-Raon-Speech-21B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KRAFTON/A.X-K2-Raon-Speech-21B-A3B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("KRAFTON/A.X-K2-Raon-Speech-21B-A3B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add fourth speech sample to Korean README
Browse files- README_ko.md +4 -0
README_ko.md
CHANGED
|
@@ -61,6 +61,10 @@ A.X K2 Raon-Speech가 대상 텍스트로부터 직접 합성한 음성 샘플
|
|
| 61 |
|
| 62 |
<audio controls><source src="https://huggingface.co/KRAFTON/A.X-K2-Raon-Speech-21B-A3B/resolve/main/samples/tts-KsponSpeech_E01426.wav" type="audio/wav"></audio>
|
| 63 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
## Architecture
|
| 65 |
|
| 66 |
| Component | Configuration |
|
|
|
|
| 61 |
|
| 62 |
<audio controls><source src="https://huggingface.co/KRAFTON/A.X-K2-Raon-Speech-21B-A3B/resolve/main/samples/tts-KsponSpeech_E01426.wav" type="audio/wav"></audio>
|
| 63 |
|
| 64 |
+
> 그래서 그거 좀 음 좀 얘기 하고 있어. 자기는 아무튼 브랜드 할 생각은 없어.
|
| 65 |
+
|
| 66 |
+
<audio controls><source src="https://huggingface.co/KRAFTON/A.X-K2-Raon-Speech-21B-A3B/resolve/main/samples/tts-KsponSpeech_E00707.wav" type="audio/wav"></audio>
|
| 67 |
+
|
| 68 |
## Architecture
|
| 69 |
|
| 70 |
| Component | Configuration |
|