cdli/whisper-small_finetuned_ghanian_ga_standard_speech_v1.0
This is a fine-tuned version of **`openai/whisper-small`** for Ga standard speech. It is part of CDLI's effort to make speech technology work for people whose speech is underserved by mainstream ASR systems.
All CDLI models and datasets can be found on **CDLI's HuggingFace page**.
Dataset
The model has been fine-tuned using `cdli/ghanian_ga_standard_speech_v1.0`.
Training
The train split was used for training, and the dev split for selecting the best checkpoint.
This Whisper model was fine-tuned and is decoded using the Yoruba (yo) language setting — out of all languages Whisper supports, the one most similar to Ga.
All model parameters (encoder, decoder, and output projection) were fine-tuned.
Evaluation
This model was evaluated on the `test` split of the dataset. Utterances longer than 30 seconds were excluded:
- Examples evaluated: 2025
- Speakers: 22
For decoding we ran Whisper with language=yo, task=transcribe, greedy search (num_beams=1, do_sample=False).
We report two complementary word error rate (WER) metrics, both computed on text normalized with Whisper's BasicTextNormalizer:
- Standard (corpus-level) WER — the usual error rate, pooling all reference words and edit errors across the entire test set.
- Per-utterance averaged WER — WER computed separately for each utterance, each capped at 1.0, then averaged across utterances.
The per-utterance averaged WER bounds each utterance to [0, 1] and weights all utterances equally, so it reflects typical performance without a few catastrophic utterances dominating — but it is not a true error rate and isn't directly comparable to other published WER, hence we report the standard, corpus-level WER as well.
Results
Overall Results
Detailed Analysis
Aggregated results can hide important underlying patterns, so we also break the WER down by subset: per speaker, and — where speaker severity is available — per impairment severity group.
Results by speaker
Per-utterance averaged WER per speaker. n_utterances is the number of test utterances for that speaker.