Automatic Speech Recognition
Transformers
Safetensors
English
Arabic
gemma3n
image-text-to-text
text-generation-inference
unsloth
egyptian
codeswitch
arabic
masry
Instructions to use oddadmix/MasriSwitch-Gemma3n-Transcriber-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use oddadmix/MasriSwitch-Gemma3n-Transcriber-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="oddadmix/MasriSwitch-Gemma3n-Transcriber-v1")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("oddadmix/MasriSwitch-Gemma3n-Transcriber-v1") model = AutoModelForImageTextToText.from_pretrained("oddadmix/MasriSwitch-Gemma3n-Transcriber-v1") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Unsloth Studio new
How to use oddadmix/MasriSwitch-Gemma3n-Transcriber-v1 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for oddadmix/MasriSwitch-Gemma3n-Transcriber-v1 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for oddadmix/MasriSwitch-Gemma3n-Transcriber-v1 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for oddadmix/MasriSwitch-Gemma3n-Transcriber-v1 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="oddadmix/MasriSwitch-Gemma3n-Transcriber-v1", max_seq_length=2048, )
Unsupported Model Architectures on Hugging Face
#2
by rawanmo7amed - opened
When I tried using the model on Hugging Face, it showed the error “cannot import Gemma3nForConditionalGeneration” because the Gemma3n architecture is not supported yet in Transformers. This means the model cannot be loaded at all for now. I would like to know when this architecture will be officially supported, because the model seems useful but is currently unusable.
Please update to the latest transformers
pip install -U transformers
oddadmix changed discussion status to closed