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: WhpTiny-hi-v2
    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: 43.666169895678095

WhpTiny-hi-v2

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

Loss: 1.0825
Wer: 43.6662

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
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1627	7.01	1000	0.5714	40.9378
0.0275	14.02	2000	0.7620	42.5943
0.0032	22.0	3000	0.9561	43.0443
0.0012	29.01	4000	1.0517	43.4426
0.0008	36.02	5000	1.0825	43.6662

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.10.0
Datasets 2.7.1.dev0
Tokenizers 0.13.2