Whisper base mixed-English
This model is a fine-tuned version of openai/whisper-base on the "en" datasets:
- mozilla-foundation/common_voice_17_0
- google/fleurs
- facebook/voxpopuli
It achieves the following results on the evaluation set:
- Loss: 0.5065
- Wer: 19.9389
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: 64
- eval_batch_size: 16
- 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: 5000
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.2909 | 0.2 | 1000 | 0.5348 | 21.1519 |
0.2316 | 0.4 | 2000 | 0.5255 | 20.7474 |
0.2351 | 0.6 | 3000 | 0.5132 | 20.3192 |
0.1924 | 0.8 | 4000 | 0.5097 | 20.0584 |
0.1984 | 1.0 | 5000 | 0.5065 | 19.9389 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 15
Unable to determine this model's library. Check the
docs
.
Model tree for deepdml/whisper-base-mix-en
Base model
openai/whisper-baseDatasets used to train deepdml/whisper-base-mix-en
Evaluation results
- Wer on Common Voice 17.0test set self-reported19.939
- WER on google/fleurstest set self-reported11.250
- WER on facebook/voxpopulitest set self-reported11.280