metadata

language:
  - ar
license: apache-2.0
datasets:
  - mozilla-foundation/common_voice_13_0
metrics:
  - wer
pipeline_tag: automatic-speech-recognition
base_model: openai/whisper-small
model-index:
  - name: whisper_small_hi_flax
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 13.0
          type: mozilla-foundation/common_voice_13_0
          config: hi
          split: test
        metrics:
          - type: wer
            value: 33.96828
            name: Wer

Whisper Small Hi - Sanchit Gandhi

This model is a fine-tuned version of openai/whisper-small on the Common Voice 13.0 dataset in Flax. It is trained using the Transformers Flax examples script, and achieves the following results on the evaluation set:

Loss: 0.02091
Wer: 33.96828

The training run can be reproduced in approximately 25 minutes by executing the script run.sh.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-04
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_train_epochs: 10

Training results

See Tensorboard logs for details.