metadata

language:
  - hi
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small Hi gpu
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: hi
          split: test
          args: 'config: hi, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 194.9420130364852

Whisper Small Hi gpu

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

Loss: 2.8500
Wer: 194.9420

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: 32
eval_batch_size: 16
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

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
8.6847	2.44	500	8.6186	184.5213
7.0074	4.88	1000	6.9394	502.2010
5.0316	7.32	1500	4.9749	693.9939
3.7844	9.76	2000	3.7445	447.2488
3.2504	12.2	2500	3.2245	326.1619
3.0134	14.63	3000	2.9979	217.9463
2.8995	17.07	3500	2.8893	213.6164
2.8678	19.51	4000	2.8500	194.9420

Framework versions

Transformers 4.33.1
Pytorch 2.0.1+rocm5.4.2
Datasets 2.14.5
Tokenizers 0.12.1