metadata

language:
  - hi
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small Hi - Shiv Kumar Ganesh
    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: hi
        metrics:
          - name: Wer
            type: wer
            value: 21.30001146394589

Whisper Small Hi - Shiv Kumar Ganesh

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: 0.6273
Wer: 21.3000

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: 64
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: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0036	14.01	1000	0.4864	21.9993
0.001	28.01	2000	0.5495	21.9592
0.0001	43.01	3000	0.5957	21.2026
0.0	57.01	4000	0.6168	21.4032
0.0	72.01	5000	0.6273	21.3000

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.12.1+cu113
Datasets 2.7.1.dev0
Tokenizers 0.13.2