Automatic Speech Recognition
Transformers
Safetensors
Japanese
moss_transcribe_diarize
text2text-generation
asr
japanese
custom_code
Instructions to use rose3/moss-anime with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rose3/moss-anime with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="rose3/moss-anime", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("rose3/moss-anime", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("rose3/moss-anime", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from rose3/moss-anime: direct link, hf CLI and curl.
- Browser
- Download file 292 Bytes
-
https://huggingface.co/rose3/moss-anime/resolve/main/processor_config.json
- Command line
-
hf download hf://rose3/moss-anime/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/rose3/moss-anime/resolve/main/processor_config.json
292 Bytes
| { | |
| "processor_class": "MossTranscribeDiarizeProcessor", | |
| "auto_map": { | |
| "AutoProcessor": "processing_moss_transcribe_diarize.MossTranscribeDiarizeProcessor" | |
| }, | |
| "audio_tokens_per_second": 12.5, | |
| "audio_merge_size": 4, | |
| "time_marker_every_seconds": 5, | |
| "enable_time_marker": true | |
| } | |