Downloads · 30 days
30
40% of all-time downloads
KasuleTrevor/qwen3-asr-lg-atypical-promptless-specaug-full
qwen3-asr-lg-atypical-promptless-specaug-full is a automatic speech recognition model from KasuleTrevor. Use it when you need speech turned into text.
This repository contains the validation-selected full checkpoint from the promptless Qwen3-ASR atypical-Luganda architectural ablation.
Downloads · 30 days
30
40% of all-time downloads
All-time downloads
75
Public
Parameters
2B
4.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors4.1 GB · 100%
From the Hugging Face model README
This repository contains the validation-selected full checkpoint from the promptless Qwen3-ASR atypical-Luganda architectural ablation.
KasuleTrevor/cdli-qwen3-asr-lg-typical-1p7b-base-finetunecdli/ugandan_luganda_nonstandard_speech_v1.0full0.0001cosine424 / 416| Setting | Value |
|---|---|
| Probability | 0.5 |
| Time masks | 2 |
| Time width | 40 |
| Frequency masks | 2 |
| Frequency width | 12 |
| Metric | Value |
|---|---|
| Total | 2,038,052,480 |
| Trainable | 2,038,052,480 |
| Trainable % | 100.0000% |
Selection was performed on the validation split only using normalized corpus WER/CER.
| Metric | Value |
|---|---|
| Selected checkpoint | checkpoint-1250 |
| Mean capped WER | 65.47% |
| Mean capped CER | 31.81% |
| Corpus WER | 75.01% |
| Corpus CER | 34.06% |
Primary reporting uses normalized per-utterance WER/CER, capped at 1.0 per utterance and then averaged. Normalized corpus metrics are retained as secondary diagnostics.
| Metric | Result |
|---|---|
| Mean capped utterance WER | 58.79% |
| Mean capped utterance CER | 23.33% |
| Normalized corpus WER | 67.27% |
| Normalized corpus CER | 28.79% |
| Relative primary WER reduction vs base | 23.33% |
| Group | n | Speakers | Mean capped WER | Mean capped CER | Corpus WER | Corpus CER |
|---|---|---|---|---|---|---|
| Mild (easily understood with minimal effort) | 366 | 3 | 53.25% | 18.06% | 60.98% | 23.73% |
| Moderate (requires effort to understand) | 347 | 3 | 58.79% | 21.82% | 63.06% | 22.64% |
| Severe (frequent breakdowns) | 315 | 3 | 65.21% | 31.13% | 79.52% | 43.09% |
| Group | n | Speakers | Mean capped WER | Mean capped CER | Corpus WER | Corpus CER |
|---|---|---|---|---|---|---|
| Articulation Disorders | 209 | 2 | 59.23% | 18.58% | 64.84% | 23.91% |
| Dysarthria | 276 | 2 | 53.33% | 19.43% | 58.02% | 22.71% |
| Stuttering (Disfluency Disorders) | 438 | 4 | 58.76% | 24.33% | 64.52% | 25.87% |
| Voice disorder | 105 | 1 | 72.35% | 38.92% | 93.06% | 53.70% |
The exact corrected trainer is archived in this repository under:
code/qwen3_asr_sft_fixed_ablation.py
The companion private results repository is:
KasuleTrevor/qwen3-asr-lg-atypical-promptless-specaug-results
No raw participant audio is redistributed.