Audio-Text-to-Text
PEFT
Safetensors
English
moss_audio
audio-captioning
vocal-bursts
lora
custom_code
Instructions to use laion/moss-voice-captioner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use laion/moss-voice-captioner with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Release complete MOSS base weights and trained caption LoRA with inference, training and licensing
4d191c8 verified Download processor_config.json from laion/moss-voice-captioner: direct link, hf CLI and curl.
- Browser
- Download file 427 Bytes
-
https://huggingface.co/laion/moss-voice-captioner/resolve/main/processor_config.json
- Command line
-
hf download hf://laion/moss-voice-captioner/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/laion/moss-voice-captioner/resolve/main/processor_config.json
427 Bytes
| { | |
| "processor_class": "MossAudioProcessor", | |
| "auto_map": { | |
| "AutoProcessor": "processing_moss_audio.MossAudioProcessor" | |
| }, | |
| "mel_config": { | |
| "mel_sr": 16000, | |
| "mel_dim": 128, | |
| "mel_n_fft": 400, | |
| "mel_hop_length": 160, | |
| "mel_dtype": "bfloat16", | |
| "use_whisper_feature_extractor": true | |
| }, | |
| "enable_time_marker": true, | |
| "audio_token_id": 151654, | |
| "audio_start_id": 151669, | |
| "audio_end_id": 151670 | |
| } | |