metadata

language:
  - sq
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_Albanian
model-index:
  - name: Whisper tiny Albanian Test
    results: []

Whisper tiny Albanian Test

This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 16 Albanian dataset. It achieves the following results on the evaluation set:

eval_loss: 1.0015
eval_wer: 51.0387
eval_runtime: 134.3539
eval_samples_per_second: 2.858
eval_steps_per_second: 0.357
epoch: 37.04
step: 2000

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: 500
training_steps: 4000

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.17.0
Tokenizers 0.15.1