Transformers
Safetensors
Yoruba
qwen2_audio
text2text-generation
audio
asr
speech-recognition
yoruba
low-resource
lora
qwen2-audio
Instructions to use Simih/yoruba_asr_audio_llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Simih/yoruba_asr_audio_llm with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Simih/yoruba_asr_audio_llm") model = AutoModelForMultimodalLM.from_pretrained("Simih/yoruba_asr_audio_llm") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 1d58f9ef4568e173630dab72bc1c2a954a3af6e99e43d15220870c4645308115
- Size of remote file:
- 12 MB
- SHA256:
- b5934470dea21b3729dae6a3bb5d5012e8e542f5b313ab9da7c541a0154c05d6
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.