---
library_name: peft
datasets:
- mozilla-foundation/common_voice_17_0
language:
- bn
base_model:
- openai/whisper-base
license: apache-2.0
metrics:
- wer
pipeline_tag: automatic-speech-recognition
model-index:
- name: Whisper Base Bn LoRA Adapter - BanglaBridge
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Common Voice 17.0
      type: mozilla-foundation/common_voice_17_0
      config: bn
      split: None
      args: 'config: bn, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 22.56397
---

# Whisper Base Bn LoRA Adapter - by BanglaBridge

This model is a PEFT LoRA fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Common Voice 17.0 dataset.
It achieves the following results on the test set:
- Wer: 44.93734
- Normalized Wer: 22.56397


### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 1e-03
- train_batch_size: 32
- eval_batch_size: 32
- warmup_steps: 500
- training_steps: 20000

LoraConfig:
- r: 32
- lora_alpha: 64
- target_modules: `["q_proj", "v_proj"]`
- lora_dropout: 0.005
- bias: none


### Training results

| Step   | Training Loss | Validation Loss |
|:------:|:-------------:|:---------------:|
| 1000	 | 0.240200 	 | 0.251211        |
| 2000	 | 0.178700 	 | 0.210411        |
| 3000	 | 0.150000 	 | 0.193197        |
| 4000	 | 0.122500 	 | 0.184060        |
| 5000	 | 0.122300 	 | 0.177079        |
| 6000	 | 0.097100 	 | 0.181073        |
| 7000	 | 0.095800 	 | 0.175566        |
| 8000	 | 0.071400 	 | 0.173997        |
| 9000	 | 0.082600 	 | 0.175677        |
| 10000	 | 0.064400 	 | 0.178262        |
| 11000	 | 0.064700 	 | 0.177943        |
| 12000	 | 0.046900 	 | 0.185763        |
| 13000	 | 0.047200 	 | 0.186843        |
| 14000	 | 0.037500 	 | 0.193575        |
| 15000	 | 0.036000 	 | 0.199084        |
| 16000	 | 0.027500 	 | 0.208745        |
| 17000	 | 0.025200 	 | 0.215685        |
| 18000	 | 0.017400 	 | 0.227938        |
| 19000	 | 0.016500 	 | 0.236160        |
| 20000	 | 0.013000 	 | 0.240447        |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.19.1
- Peft 0.10.0