metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
datasets:
  - razhan/DOLMA-speech
metrics:
  - wer
model-index:
  - name: whisper-base-hac-telegram
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: razhan/DOLMA-speech gilaki
          type: razhan/DOLMA-speech
          args: gilaki
        metrics:
          - name: Wer
            type: wer
            value: 1.0472082810539523

whisper-base-hac-telegram

This model is a fine-tuned version of openai/whisper-base on the razhan/DOLMA-speech gilaki dataset. It achieves the following results on the evaluation set:

Loss: 2.6806
Wer: 1.0472
Cer: 0.5468

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: 256
eval_batch_size: 128
seed: 42
distributed_type: multi-GPU
num_devices: 2
total_train_batch_size: 512
total_eval_batch_size: 256
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 5.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
No log	1.0	6	3.5224	1.1311	0.5560
2.4889	2.0	12	3.4807	1.0566	0.5018
2.4889	3.0	18	3.2108	1.0561	0.4986
2.3707	4.0	24	2.9445	1.0583	0.5155
2.0528	5.0	30	2.6806	1.0472	0.5468

Framework versions

Transformers 4.49.0.dev0
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.21.0