metadata
language:
- bn
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_0
metrics:
- wer
base_model: arun100/whisper-base-bn
model-index:
- name: Whisper Base Bengali
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: mozilla-foundation/common_voice_16_0 bn
type: mozilla-foundation/common_voice_16_0
config: bn
split: test
args: bn
metrics:
- type: wer
value: 35.60262364321316
name: Wer
- type: wer
value: 29.87
name: WER
Whisper Base Bengali
This model is a fine-tuned version of arun100/whisper-base-bn on the mozilla-foundation/common_voice_16_0 bn dataset. It achieves the following results on the evaluation set:
- Loss: 0.2671
- Wer: 35.6026
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: 1e-06
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.2423 | 1.72 | 500 | 0.2710 | 35.9570 |
0.2329 | 3.43 | 1000 | 0.2671 | 35.6026 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.2.dev0
- Tokenizers 0.15.0