mascir_fr_wav2vec_test

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

• Loss: 0.0136
• Wer: 0.1612

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	8.06	250	3.7503	0.9919
8.0637	16.13	500	3.0132	0.9919
8.0637	24.19	750	2.9734	0.9919
2.9339	32.26	1000	2.0538	0.9963
2.9339	40.32	1250	0.4530	0.5406
0.9878	48.39	1500	0.1807	0.3373
0.9878	56.45	1750	0.0814	0.2436
0.3416	64.52	2000	0.0512	0.2114
0.3416	72.58	2250	0.0292	0.1823
0.1952	80.65	2500	0.0198	0.1742
0.1952	88.71	2750	0.0158	0.1631
0.1476	96.77	3000	0.0136	0.1612

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.1
• Tokenizers 0.13.3