whisper-tiny-german-V2-HanNeurAI
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: 0.5818
- Wer: 32.3327
This fine-tuning model is part of my school project. With limitation of my compute, I scale down the dataset from german common voice to shuffled 200k rows
Additional information can be found in this github: HanCreation/Whisper-Tiny-German
Model description
Model Parameter (pipe.model.num_parameters()): 37760640 (37M)
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: 8000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.2054 | 0.08 | 1000 | 0.7062 | 39.0698 |
0.1861 | 0.16 | 2000 | 0.6687 | 36.4857 |
0.1677 | 0.24 | 3000 | 0.6393 | 35.6849 |
0.2019 | 0.32 | 4000 | 0.6193 | 34.4385 |
0.1808 | 0.4 | 5000 | 0.6103 | 33.8459 |
0.1697 | 0.48 | 6000 | 0.5956 | 32.8519 |
0.1468 | 0.56 | 7000 | 0.5884 | 32.7029 |
0.1906 | 0.64 | 8000 | 0.5818 | 32.3327 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for LiquAId/whisper-tiny-german-V2-HanNeurAI
Base model
openai/whisper-tinyDataset used to train LiquAId/whisper-tiny-german-V2-HanNeurAI
Evaluation results
- Wer on Common Voice 11.0 German shuffled 200k rowstest set self-reported32.333