Audio-Text-to-Text
Transformers
Safetensors
Chinese
qwen2_audio
text2text-generation
telecom-fraud
audio-text
qwen2-audio
chinese
speech-understanding
supervised-fine-tuning
Instructions to use JimmyMa99/AntiFraud-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JimmyMa99/AntiFraud-SFT with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("JimmyMa99/AntiFraud-SFT") model = AutoModelForMultimodalLM.from_pretrained("JimmyMa99/AntiFraud-SFT") - Notebooks
- Google Colab
- Kaggle
File size: 153 Bytes
00ce8ee | 1 2 3 4 5 6 7 | {
"audio_bos_token": "<|audio_bos|>",
"audio_eos_token": "<|audio_eos|>",
"audio_token": "<|AUDIO|>",
"processor_class": "Qwen2AudioProcessor"
}
|