Hugging Face's logo

CKSINGH
/
whisper-medium-hi

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Hindi
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-medium-hi / README.md
CKSINGH's picture
CKSINGH
End of training
261a116
preview code
|
raw
history blame
No virus
1.61 kB
metadata
language:
  - hi
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper Medium Hi - CKS 0911
    results: []

Whisper Medium Hi - CKS 0911

This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1623
  • Wer: 87.6048

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: 2
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1
  • training_steps: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
1.5395 0.04 1 1.3495 82.6772
1.6679 0.08 2 1.1623 87.6048

Framework versions

  • Transformers 4.36.0.dev0
  • Pytorch 2.1.0
  • Datasets 2.14.6
  • Tokenizers 0.14.1