wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod5

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the xtreme_s dataset. It achieves the following results on the evaluation set:

• Loss: 0.9790
• Wer: 0.5366

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: 0.001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 600
• num_epochs: 60
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.9955	9.23	300	2.8534	1.0
1.7522	18.46	600	0.7939	0.7079
0.3374	27.69	900	0.8635	0.6423
0.1617	36.92	1200	0.9916	0.5929
0.1102	46.15	1500	0.9796	0.5648
0.0815	55.38	1800	0.9790	0.5366

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1