GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Gemmar
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Gemmar
Model Tree
Gemmar/luganda-agr-asr-whisper-small-stage1
Input Modalities
Output Modalities
Supported Functionality
| Test set | WER | CER | 95% CI (WER) |
|---|---|---|---|
| T2 — Yogera Agricultural (n=11,679) | 34.92% | 13.09% | [34.47, 35.42] |
| T1 — Common Voice 25 general (n=11,823) | 52.7% | 50.56% | [42.74, 62.55] |
Stage-2 effect vs the Stage-1 model (Gemmar/luganda-agr-asr-whisper-small-stage1): T2 WER 34.94% → 34.92% (Δ -0.02 pp) · T1 WER 46.50% → 52.7% (Δ 6.20 pp, catastrophic-forgetting check).
Bootstrap CIs: 1,000 resamples with replacement, seed 42. Text normalisation: lowercase, punctuation stripped (apostrophes kept), whitespace collapsed — identical across all nine experimental conditions (E1–E9).
python
from transformers import pipeline asr = pipeline("automatic-speech-recognition", model="Gemmar/luganda-agr-asr-whisper-small-stage2-rehearsal") # Force the Luganda decoding prefix (custom token added during Stage 1):tok = asr.tokenizerasr.model.generation_config.forced_decoder_ids = [ [1, tok.convert_tokens_to_ids("<|luganda|>")], [2, tok.convert_tokens_to_ids("<|transcribe|>")], [3, tok.convert_tokens_to_ids("<|notimestamps|>")],]asr.model.generation_config.no_repeat_ngram_size = 3 print(asr("farmer_question.wav")["text"])<|luganda|> token (added in Stage 1,
initialised as the mean of Whisper's 99 language embeddings) prepended to all
training labels and forced at inference.Built for agricultural information access in Uganda — transcribing farmers' spoken Luganda queries for advisory/retrieval systems. Trained on clean crowdsourced prompts; not validated on noisy field recordings, code-switched speech, or other Ugandan languages. Research model — verify before production use.
text
Gemmar, F. (2026). Building an ASR Model for Luganda Agricultural InformationAccess. MSc dissertation, Makerere University.from transformers import pipeline asr = pipeline("automatic-speech-recognition", model="Gemmar/luganda-agr-asr-whisper-small-stage2-rehearsal") # Force the Luganda decoding prefix (custom token added during Stage 1):tok = asr.tokenizerasr.model.generation_config.forced_decoder_ids = [ [1, tok.convert_tokens_to_ids("<|luganda|>")], [2, tok.convert_tokens_to_ids("<|transcribe|>")], [3, tok.convert_tokens_to_ids("<|notimestamps|>")],]asr.model.generation_config.no_repeat_ngram_size = 3 print(asr("farmer_question.wav")["text"])