Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Swahili
whisper
Eval Results (legacy)
Instructions to use Mollel/ASR-Swahili-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mollel/ASR-Swahili-Small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Mollel/ASR-Swahili-Small")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Mollel/ASR-Swahili-Small") model = AutoModelForSpeechSeq2Seq.from_pretrained("Mollel/ASR-Swahili-Small", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 6c3c2feb3cea65318a5f5bc8b189459ca05690e5d829f498ce58b06966a8ab73
- Size of remote file:
- 5.5 kB
- SHA256:
- 2ec319de276aa407a885fa77816c52eeff7a7b42e57dde68a6af9e7616ad278e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.