metadata
language:
- de
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper-Tiny-german-HanNeurAI
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: de
split: test
args: 'config: de, split: test'
metrics:
- name: Wer
type: wer
value: 31.434636476207324
Whisper-Tiny-german-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: 0.5505
- Wer: 31.4346
This model is part of my school project, it uses shuffled 100k rows of train dataset since the computation power is limited.
Additional information can be found in this github: HanCreation/Whisper-Tiny-German
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4824 | 0.16 | 1000 | 0.6305 | 35.5019 |
| 0.4284 | 0.32 | 2000 | 0.5855 | 33.3615 |
| 0.4152 | 0.48 | 3000 | 0.5610 | 32.1068 |
| 0.4387 | 0.64 | 4000 | 0.5505 | 31.4346 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed