metadata

language:
  - bn
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_13_0
metrics:
  - wer
base_model: openai/whisper-tiny
model-index:
  - name: Whisper tiny by ehzawad
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 13.0
          type: mozilla-foundation/common_voice_13_0
          config: bn
          split: test
          args: 'config: lt, split: test'
        metrics:
          - type: wer
            value: 75.40948582822959
            name: Wer

Whisper tiny by ehzawad

This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.2422
Wer: 75.4095

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-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3593	0.53	1000	0.3717	102.7311
0.2502	1.07	2000	0.2802	81.0367
0.2219	1.6	3000	0.2535	80.8361
0.2069	2.14	4000	0.2422	75.4095

Framework versions

Transformers 4.30.0.dev0
Pytorch 2.0.1+cu117
Datasets 2.12.0
Tokenizers 0.13.3