Any-to-Any
Transformers
Safetensors
English
Chinese
funaudiochat
text-generation
audio-language-model
speech-to-speech
Instructions to use FunAudioLLM/Fun-Audio-Chat-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FunAudioLLM/Fun-Audio-Chat-8B with Transformers:
# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("FunAudioLLM/Fun-Audio-Chat-8B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from FunAudioLLM/Fun-Audio-Chat-8B: direct link, hf CLI and curl.
- Browser
- Download file 218 Bytes
-
https://huggingface.co/FunAudioLLM/Fun-Audio-Chat-8B/resolve/main/processor_config.json
- Command line
-
hf download hf://FunAudioLLM/Fun-Audio-Chat-8B/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/FunAudioLLM/Fun-Audio-Chat-8B/resolve/main/processor_config.json
218 Bytes
| { | |
| "audio_bos_token": "<|audio_bos|>", | |
| "audio_eos_token": "<|audio_eos|>", | |
| "audio_group_size": 5, | |
| "audio_pad_token": "<|audio_pad|>", | |
| "audio_token": "<|AUDIO|>", | |
| "processor_class": "FunAudioChatProcessor" | |
| } | |