openai/whisper-small-en
This model is a fine-tuned version of openai/whisper-small-en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.21313807368278503
- Wer: 8.312998407517968
Training and evaluation data
Training data: Myst Train (125 hours) + CSLU Scripted train (35 hours) Evaluation data: Myst Dev (20.9 hours) + CSLU Scripted Dev(4.8)
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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: 10000
- converged_after: 1500
- 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.
Evaluation results
- WER on myst-testtest set self-reported12.110
- WER on cslu_scriptedtest set self-reported2.740
- WER on cslu_spontaneoustest set self-reported32.720
- WER on librispeechself-reported7.970