---
library_name: transformers
license: mit
base_model: Sunbird/asr-whisper-large-v3-salt
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: cdli-whisper-en-ug-ke-sunbird-encoder-a40
  results: []
datasets:
- cdli/ugandan_english_nonstandard_speech_v1.0
- cdli/kenyan_english_nonstandard_speech_v1.0
language:
- en
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# cdli-whisper-en-ug-ke-sunbird-encoder-a40

This model is a fine-tuned version of [Sunbird/asr-whisper-large-v3-salt](https://huggingface.co/Sunbird/asr-whisper-large-v3-salt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8885
- Wer: 0.2945
- Cer: 0.2021
- test_cer                =     0.1224
- test_loss               =     0.6973
- test_runtime            = 0:23:36.28
- test_samples_per_second =      1.369
- test_steps_per_second   =      0.342
- test_wer                =     0.1977


# Ugandan English
- utterance_avg_wer = 0.238785
- utterance_avg_cer = 0.144570
- wer = 0.255675
- cer = 0.151887

# Kenyan English
- utterance_avg_wer = 0.191583
- utterance_avg_cer = 0.114696
- wer = 0.197774
- cer = 0.119329

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 150
- training_steps: 2500

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer    | Cer    |
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|
| 0.8367        | 0.4248 | 250  | 0.9348          | 0.3188 | 0.2204 |
| 0.7745        | 0.8496 | 500  | 0.9045          | 0.3089 | 0.2130 |
| 0.6983        | 1.2736 | 750  | 0.9017          | 0.3057 | 0.2104 |
| 0.6503        | 1.6984 | 1000 | 0.8888          | 0.2970 | 0.2038 |
| 0.6562        | 2.1223 | 1250 | 0.8883          | 0.3022 | 0.2087 |
| 0.6649        | 2.5472 | 1500 | 0.8885          | 0.2978 | 0.2055 |
| 0.7165        | 2.9720 | 1750 | 0.8887          | 0.2976 | 0.2051 |
| 0.6558        | 3.3959 | 2000 | 0.8885          | 0.2958 | 0.2031 |
| 0.691         | 3.8207 | 2250 | 0.8895          | 0.2948 | 0.2019 |
| 0.5922        | 4.2447 | 2500 | 0.8885          | 0.2945 | 0.2021 |


### Framework versions

- Transformers 4.52.0
- Pytorch 2.7.1+cu118
- Datasets 3.6.0
- Tokenizers 0.21.4