--- language: - kea tags: - automatic-speech-recognition - kabuverdianu - cabo-verde - omnilingual-asr - wav2vec2 - fine-tuned - low-resource license: cc-by-nc-4.0 base_model: facebook/omnilingual-asr-ctc-300m datasets: - shunyalabs/kabuverdianu-speech-dataset metrics: - wer --- # KEA Omnilingual-ASR — Kabuverdianu Fine-Tune Fine-tuned version of [omniASR_CTC_300M](https://github.com/facebookresearch/omnilingual-asr) for **Kabuverdianu (kea)** — Cape Verdean Creole, a low-resource language spoken by ~1 million people. ## Model Details | Property | Value | |---|---| | Base model | omniASR_CTC_300M (Meta, ~300M parameters) | | Language | Kabuverdianu (`kea_Latn`) | | Task | Automatic Speech Recognition (CTC) | | Framework | [omnilingual-asr](https://github.com/facebookresearch/omnilingual-asr) (fairseq2) | | Dataset | [shunyalabs/kabuverdianu-speech-dataset](https://huggingface.co/datasets/shunyalabs/kabuverdianu-speech-dataset) | ## Training Data | Split | Samples | |---|---| | Train | 2715 | | Validation | 366 | | Test | 864 | ## Training Hyperparameters | Parameter | Value | |---|---| | Training steps | N/A | | Learning rate | N/A | | Mixed precision | N/A | | Gradient accumulation | N/A batches | | Encoder frozen for | N/A steps | | Min audio length | N/A samples (2 s) | | Max audio length | N/A samples (60 s) | | Max elements per batch | N/A | ## Evaluation Results | Metric | Value | |---|---| | WER (validation) | N/A | | Train CTC Loss | N/A | | Validation CTC Loss | N/A | ## Checkpoint Structure ``` checkpoint/sdp_00.pt ← model weights (fairseq2 sharded format) model.yaml ← architecture definition config.yaml ← full training configuration metrics/train.jsonl ← per-step training metrics metrics/valid.jsonl ← per-step validation metrics (WER) ```