whisper-base-cs-cv11-train-stretch20-gain10-pitch20-gaussian20-lowpass10

This model is a fine-tuned version of openai/whisper-base on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3660
• Wer: 35.2359

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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
0.5579	1.4440	1000	0.4514	43.2460
0.3787	2.8881	2000	0.3813	37.2012
0.2523	4.3321	3000	0.3686	35.5067
0.2408	5.7762	4000	0.3660	35.2359

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1