Promote Sign in Sign up

Audio model

wav2vec2-large-xlsr-mvc-swahili

Listed for automatic speech recognition. Explore the model card for usage and requirements.

eddiegulay Audio Open weights apache-2.0
Open model card ↗
Type
Audio
Weights
Open
Downloads
552k
Likes
3
Pipeline
automatic speech recognition
License
apache-2.0

Model hub

eddiegulay/wav2vec2-large-xlsr-mvc-swahili

Repo
eddiegulay/wav2vec2-large-xlsr-mvc-swahili
Library
transformers
Access
Public
Technical tags and languages
sw transformers tensorboard safetensors wav2vec2 automatic-speech-recognition generated_from_trainer dataset:common_voice_13_0 base_model:facebook/wav2vec2-large-xlsr-53 base_model:finetune:facebook/wav2vec2-large-xlsr-53 model-index endpoints_compatible
Open on Hugging Face