Downloads · 30 days
0
waxal-asr-solution
ravitejac/waxal-asr-solution
waxal-asr-solution is a automatic speech recognition model from ravitejac. Use it when you need speech turned into text. The card lists the license as apache-2.0.
Artifacts supporting the code review of submission GBc3jxZk in the Google WAXAL ASR Challenge (Zindi): public 0.757397 / private 0.766450, metric 1 − (WER + CER)/2, Lingala + Shona speech recognition. These checkpoint…
Access
Public
Updated Aug 20, 2026
Repo size
56.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt36.1 GB · 99%
At a glance
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Access
- Public
- Created
- Aug 19, 2026
- Updated
- Aug 20, 2026
- SHA
- e60e4bf9
Base models
Model card
From the Hugging Face model README
WAXAL ASR solution — retrained weights (Zindi code review)
Artifacts supporting the code review of submission GBc3jxZk in the
Google WAXAL ASR Challenge (Zindi): public 0.757397 / private 0.766450,
metric 1 − (WER + CER)/2, Lingala + Shona speech recognition. These
checkpoints were retrained from scratch from the recipes in the reviewed
code package; per-stage reproduction evidence ships with that package.
Contents
| Path | Artifact | Base model | License of base |
|---|---|---|---|
checkpoints/ft-7b-tta-spec/ | 7B decoder fine-tune (TTA specialist) | facebook/omniASR-LLM-7B (omnilingual-asr 0.2.0) | Apache-2.0 |
checkpoints/mwer-ttaspec-v2lr5/ | final 7B (MWER expected-risk fine-tune) | facebook/omniASR-LLM-7B | Apache-2.0 |
checkpoints/w2vbert-lin-v1/, checkpoints/w2vbert-sna-v1/ | per-language CTC fine-tunes | facebook/w2v-bert-2.0 | MIT |
corrector_v2/adapter/ | LoRA r16 error-corrector adapter | google/gemma-4-E4B-it | Apache-2.0 |
lm/, lm_screen/ | KenLM 5-gram binaries (participant-built text corpus) | KenLM (kpu/kenlm) | LGPL-2.1 (toolkit) |
phase2_lid/ | language-routing outputs (JSON) | produced with facebook/mms-lid-256 | CC-BY-NC-4.0 (no model derivative included — outputs only) |
submissions/ | per-stage prediction files (participant model outputs) | — | — |
Provenance and attribution
Fine-tuned checkpoints are derivatives of the base models above; credit to Meta AI (omnilingual ASR, w2v-BERT 2.0, MMS-LID) and Google DeepMind (Gemma). Base weights remain governed by their original licenses; no endorsement by the upstream authors is implied. Training data: the competition WaxalNLP corpus plus disclosed CC-BY-4.0 corpora (google/fleurs; AfriVoice mirrors KasuleTrevor/Lingala_100hrs, realtime-speech/shona1); full data-governance and external-data reviews are in the code package submitted to Zindi.
This repository contains no competition audio and no test-set reference transcriptions — prediction files are participant model outputs only.
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Languages
- ln, sn
- Created
- Aug 19, 2026
- Updated
- Aug 20, 2026