metadata
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 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