Audio-Text-to-Text
Transformers
Safetensors
English
Chinese
moss_transcribe_diarize
text2text-generation
moss
audio
speech
asr
diarization
timestamp-asr
long-form-audio
multimodal
multilingual
custom_code
Eval Results
Instructions to use itazap/MOSS-Transcribe-Diarize-HF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use itazap/MOSS-Transcribe-Diarize-HF with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("itazap/MOSS-Transcribe-Diarize-HF", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("itazap/MOSS-Transcribe-Diarize-HF", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from itazap/MOSS-Transcribe-Diarize-HF: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/itazap/MOSS-Transcribe-Diarize-HF/resolve/main/tokenizer.json
- Command line
-
hf download hf://itazap/MOSS-Transcribe-Diarize-HF/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/itazap/MOSS-Transcribe-Diarize-HF/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- 9fdf8a66b991d24e784a2f5bd480c8c7ce2c9c403c151ad1656793d6535573ae
- Size of remote file:
- 11.4 MB
- SHA256:
- eb21895752d2380b32ae2e2c40905c7aa6c8e55c5e6ba33cd065bf77d4d53f74
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.