teckedd/gha-whisper-small-twi-en-balanced-v7-lite-frozen

teckedd/gha-whisper-small-twi-en-balanced-v7-lite-frozen

Frozen-encoder balanced Twi/Akan + English-retention Whisper small proof checkpoint for Ghana Health AI. Validation WER 53.83% on the capped Waxal validation subset; not a production promotion candidate.

• —Base model: openai/whisper-small
• —Task: automatic-speech-recognition
• —Languages: tw, ak, en
• —Card generated: 2026-08-09 (UTC)
• —Product: ghanahealth.serendepify.com

Not a medical device. Outputs support community health guidance only.

Metrics

Training data

• —google/WaxalNLP (aka_asr)
• —fsicoli/common_voice_22_0 (tw)
• —fsicoli/common_voice_22_0 (en)
• —ghananlpcommunity/twi-speech-text-multispeaker-16k (default)

Intended use

• —In-product ASR / TTS / chat for Twi (Akan) and English health conversations in Ghana.
• —Research on low-resource Ghanaian language speech and health dialogue.

Out of scope

• —Clinical diagnosis or autonomous medical decisions.
• —Claiming near-native quality without reporting held-out WER/CER or human A/B scores.

How to load

from transformers import pipeline  # or AutoModel + processor per task
# repo: teckedd/gha-whisper-small-twi-en-balanced-v7-lite-frozen

Citation

If you use this checkpoint, please credit Ghana Health AI / Serendepify and the upstream base model authors plus any listed datasets.