Automatic Speech Recognition
Transformers
Safetensors
English
whisper
text-generation-inference
unsloth
Instructions to use iBala/maragatham with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use iBala/maragatham with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="iBala/maragatham")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("iBala/maragatham") model = AutoModelForSpeechSeq2Seq.from_pretrained("iBala/maragatham", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Uploaded finetuned model
- Developed by: iBala
- License: apache-2.0
- Finetuned from model : unsloth/whisper-large-v3
This whisper model was trained 2x faster with Unsloth and Huggingface's TRL library.
Credits
Unsloth for model training https://huggingface.co/datasets/SPRINGLab/SPRING_INX_Tamil_R2 - The data set used.
This is used for learning purposes only.
- Downloads last month
- 9
