finetune_wav2vec2_960h_thirty

This model is a fine-tuned version of facebook/wav2vec2-base-960h on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7088
• Wer: 30.8513
• Cer: 15.3422

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2000
• training_steps: 3800

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.9521	2.8090	1000	0.7088	30.8513	15.3422
0.6771	5.6180	2000	0.5857	26.9346	13.3483
0.5499	8.4270	3000	0.5207	24.7273	12.1108

Framework versions

• Transformers 4.40.2
• Pytorch 2.1.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1