README.md

metadata

language:
  - ta
  - ml
  - mr
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: ./whisper-medium-ta-ml-mr
    results: []

./whisper-medium-ta-ml-mr

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

• Loss: 0.2549
• Wer: 98.6642

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• training_steps: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6325	0.4	50	0.3366	97.8901
0.2317	0.8	100	0.2549	98.6642

Framework versions

• Transformers 4.37.0
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.1