ctaguchi
/

killkan_asr

Automatic Speech Recognition Transformers Safetensors Imbabura Highland Quichua Chimborazo Highland Quichua wav2vec2 audio speech low-resource Inference Endpoints

Model card Files Files and versions Community

Edit model card

Killkan-ASR

Killkan (Kichwa uyashkata payLLatak Killkak ANta "Kichwa Automatic Speech Transcriber) is an automatic speech recognition dataset for Kichwa, and Killkan-ASR is the ASR model based on the dataset.

Downloads last month: 9

Safetensors

Model size

316M params

Tensor type

F32

Killkan-ASR

Finetuned from facebook/wav2vec2-large-xlsr-53

Finetuned from