Cdli Qwen3 Asr Lg Atypical Stage3 1p7b Base B8
This repo contains the selected checkpoint checkpoint-1000 from the LG-QWEN3-ASR-ATYPICAL-STAGE3-1P7B-BASE-B8 run.
Modellquelle
- Art
- Text model
- Dateigröße
- 3,80 GB
- Basismodell
- KasuleTrevor/cdli-qwen3-asr-lg-typical-1p7b-base-finetune
- Version
- vmodel
- Aktualisiert
- 22. Sept. 2026
- Downloads
- 8
- Quelle
- Hugging Face
Quellenbeschreibung
CDLI Qwen3-ASR Luganda Atypical Speech Fine-tune
This repo contains the selected checkpoint checkpoint-1000 from the LG-QWEN3-ASR-ATYPICAL-STAGE3-1P7B-BASE-B8 run.
Training Setup
- Base model: KasuleTrevor/cdli-qwen3-asr-lg-typical-1p7b-base-finetune
- Dataset: cdli/ugandan_luganda_nonstandard_speech_v1.0
- Split files:
train_cleaned.tsv,validation_cleaned.tsv,test_cleaned.tsv - Training language tag:
Luganda - Forced inference language: disabled
- Epochs: 10
- Batch size: 4
- Gradient accumulation: 4
- Learning rate: 0.0001
- Scheduler: cosine
- Warmup ratio: 0.03
- Save steps: 500
- Selected checkpoint: checkpoint-1000
- Selection reason: fallback best eval_loss (0.512122)
Final Test Metrics
- Primary WER: avg utterance WER normalized, capped at 1.0 = 0.497477
- Primary CER: avg utterance CER normalized, capped at 1.0 = 0.230633
- Corpus WER (normalized, uncapped): 0.633333
- Corpus CER (normalized, uncapped): 0.322517
Checkpoint Selection Evidence
| checkpoint | step | eval_loss |
|---|---|---|
| checkpoint-1000 | 1000 | 0.5121216177940369 |
Severity Breakdown
| severity_speech_impairment | n_samples | n_speakers | mean_wer | mean_cer | median_wer | median_cer |
|---|---|---|---|---|---|---|
| Severe (frequent breakdowns) | 315 | 3 | 0.5971 | 0.3095 | 0.6 | 0.2698 |
| Moderate (requires effort to understand) | 347 | 3 | 0.5123 | 0.2329 | 0.5 | 0.1667 |
| Mild (easily understood with minimal effort) | 365 | 3 | 0.3975 | 0.1604 | 0.375 | 0.102 |
Artifacts
- Result folder:
results/checkpoint-1000/ - Includes checkpoint validation summaries, final test predictions, scored outputs, and grouped metadata analyses.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 22. Sept.
Modellartefakte
1 Artefakt
Modellartefakte
1 ArtefaktQuellenauszüge
2 Auszüge
Quellenauszüge
2 Auszüge--- base_model: KasuleTrevor/cdli-qwen3-asr-lg-typical-1p7b-base-finetune pipeline_tag: automatic-speech-recognition library_name: transformers license: apache-2.0 language: - lg tags: - automatic-speech-recognition - qwen3-asr - luganda - atypical-speech - stage3 datasets: - cdli/ugandan_luganda_nonstandard_speech_v1.0 --- # CDLI Qwen3-ASR Luganda Atypical Speech Fine-tune This repo contains the selected checkpoint `checkpoint-1000` from the `LG-QWEN3-ASR-ATYPICAL-STAGE3-1P7B-BASE-B8` run. ## Training Setup - Base model: KasuleTrevor/cdli-qwen3-asr-lg-typical-1p7b-base-finetune - Dataset: cdli/ugandan_luganda_nonstandard_speech_v1.0 - Split files: `train_cleaned.tsv`, `validation_cleaned.tsv`, `test_cleaned.tsv` - Training language tag: `Luganda` - Forced inference language: disabled - Epochs: 10 - Batch size: 4 - Gradient accumulation: 4 - Learning rate: 0.0001 - Scheduler: cosine - Warmup ratio: 0.03 - Save steps: 500 - Selected checkpoint: checkpoint-1000 - Selection reason: fallback best eval_loss (0.512122) ## Final Test Metrics - Primary WER: avg utterance WER normalized, capped at 1.0 = 0.497477 - Primary CER: avg utterance CER normalized, capped at 1.0 = 0.230633 - Corpus WER (normalized, uncapped): 0.633333 - Corpus CER (normalized, uncapped): 0.322517 ## Checkpoint Selection Evidence | checkpoint | step | eval_loss | | --- | --- | --- | | checkpoint-1000 | 1000 | 0.5121216177940369 | ## Severity Breakdown | severity_speech_impairment | n_samples | n_speakers | mean_wer | mean_cer | median_wer | median_cer | | --- | --- | --- | --- | --- | --- | --- | | Severe (frequent breakdowns) | 315 | 3 | 0.5971 | 0.3095 | 0.6 | 0.2698 | | Moderate (requires effort to understand) | 347 | 3 | 0.5123 | 0.2329 | 0.5 | 0.1667 | | Mild (easily understood with minimal effort) | 365 | 3 | 0.3975 | 0.1604 | 0.375 | 0.102 | ## Artifacts - Result folder: `results/checkpoint-1000/` - Includes checkpoint validation summaries, final test predictions, scored outputs, and grouped metadata analyses.
Source context: 8 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo KasuleTrevor/cdli-qwen3-asr-lg-atypical-stage3-1p7b-base-b8
