Hugging Face's logo

Samveg17
/
whisper-base-hi

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Hindi
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-base-hi / README.md
Bhansali
update model card README.md
4fd0b40
preview code
|
raw history blame contribute delete
No virus
1.65 kB
metadata
language:
  - hi
license: apache-2.0
base_model: openai/whisper-base
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - google/fleurs
metrics:
  - wer
model-index:
  - name: Whisper_Samveg17@
    results: []

Whisper_Samveg17@

This model is a fine-tuned version of openai/whisper-base on the Google Fleurs dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5117
  • Wer: 37.9539

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: 8
  • 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

Training results

Training Loss Epoch Step Validation Loss Wer
0.1401 4.72 1000 0.3607 39.9494
0.0174 9.43 2000 0.4239 38.9954
0.0022 14.15 3000 0.4867 38.4698
0.001 18.87 4000 0.5117 37.9539

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3