Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-medium-finetuned
This model is a fine-tuned version of openai/whisper-medium on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:
- eval_loss: 1.8759
- eval_wer: 45.1163
- eval_runtime: 32.2649
- eval_samples_per_second: 0.62
- eval_steps_per_second: 0.031
- epoch: 99.01
- step: 100
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: 0.0001
- 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: constant_with_warmup
- lr_scheduler_warmup_steps: 10
- training_steps: 100
- mixed_precision_training: Native AMP
Framework versions
- PEFT 0.11.1
- Transformers 4.42.3
- Pytorch 2.6.0+cu124
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 8
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for evanmazor/whisper-medium-finetuned
Base model
openai/whisper-medium