metadata

language:
  - zh
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
model-index:
  - name: Whisper tiny epoch 1- Perrie
    results: []

Whisper tiny epoch 1- Perrie

This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.4304
Cer: 60.2188

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: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 70
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.3925	1.0	705	0.4304	60.2188

Framework versions

Transformers 4.35.0.dev0
Pytorch 1.12.1
Datasets 2.14.6
Tokenizers 0.14.1