metadata

license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-medium-custom-hi
    results: []

whisper-medium-custom-hi

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: 0.3271
Wer: 0.2435

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: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
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: 500
training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0233	4.89	1000	0.2673	0.2642
0.0003	9.78	2000	0.3271	0.2435

Framework versions

Transformers 4.32.0.dev0
Pytorch 2.0.1+cu117
Datasets 2.14.4
Tokenizers 0.13.3