Hugging Face's logo

gopikachu
/
whisper-medium-hi-4cycles

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Hindi
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-medium-hi-4cycles / README.md
gopikachu's picture
gopikachu
End of training
1afdbfe verified
preview code
|
raw
history blame
1.46 kB
metadata
language:
  - hi
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - konnakol-whisper-medium-hi-4cycles
model-index:
  - name: Whisper Medium Hi - Gopika
    results: []

Whisper Medium Hi - Gopika

This model is a fine-tuned version of openai/whisper-medium on the Konnakol - MASC - longer segments dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.1149
  • eval_wer: 0.0217
  • eval_cer: 0.0212
  • eval_runtime: 15.826
  • eval_samples_per_second: 2.907
  • eval_steps_per_second: 0.19
  • epoch: 25.0
  • step: 150

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: 5e-05
  • train_batch_size: 32
  • eval_batch_size: 16
  • 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: 1000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.41.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1