metadata

license: apache-2.0
base_model: bayartsogt/whisper-small-mn-8
tags:
  - generated_from_trainer
datasets:
  - common_voice_11_0
model-index:
  - name: whisper-small-mongolian
    results: []

whisper-small-mongolian

This model is a fine-tuned version of bayartsogt/whisper-small-mn-8 on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

eval_loss: 0.0255
eval_wer: 3.9864
eval_runtime: 1588.8988
eval_samples_per_second: 1.17
eval_steps_per_second: 0.147
epoch: 2.3112
step: 1500

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: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1000
training_steps: 3000
mixed_precision_training: Native AMP

Framework versions

Transformers 4.40.1
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1