Hugging Face's logo

Kurokabe
/
whisper-small-bn

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Bengali
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-small-bn / README.md
Kurokabe's picture
Kurokabe
update model card README.md
06e934e
preview code
|
raw
history blame contribute delete
No virus
1.42 kB
metadata
language:
  - bn
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
model-index:
  - name: whisper-small bengali
    results: []

whisper-small bengali

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

  • eval_loss: 0.1069
  • eval_wer_ortho: 0.3909
  • eval_wer: 0.1697
  • eval_runtime: 31948.7278
  • eval_samples_per_second: 0.926
  • eval_steps_per_second: 0.463
  • epoch: 0.1
  • step: 1500

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: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant_with_warmup
  • lr_scheduler_warmup_steps: 50
  • training_steps: 4000

Framework versions

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