metadata

language:
  - mn
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_1
  - google/fleurs
model-index:
  - name: Whisper Large V2 MN - Ankhbayasgalan Davaadorj
    results: []

Whisper Large V2 MN - Ankhbayasgalan Davaadorj

This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 16.1 & FLEURS dataset. It achieves the following results on the evaluation set:

eval_loss: 0.2431
eval_wer: 19.6462
eval_runtime: 212.4702
eval_samples_per_second: 0.48
eval_steps_per_second: 0.122
epoch: 10.99
step: 1000

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: 8
eval_batch_size: 4
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: 2000
mixed_precision_training: Native AMP

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.2.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2