Hugging Face's logo

rishikksh20
/
whisper-small-hi

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-small-hi / README.md
rishikksh20's picture
rishikksh20
End of training
4483189 verified
preview code
|
raw
history blame contribute delete
1.44 kB
metadata
language:
  - en
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - deepsync-ai/translation-hi-en-whisper
model-index:
  - name: Hindi to English Translation
    results: []

Hindi to English Translation

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

  • eval_loss: 1.4841
  • eval_wer: 70.4717
  • eval_runtime: 468.5856
  • eval_samples_per_second: 2.313
  • eval_steps_per_second: 0.29
  • epoch: 1.6393
  • step: 1000

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

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1