wav2vec2-large-xlsr-53-french-KM-v6

This model is a fine-tuned version of Ilyes/wav2vec2-large-xlsr-53-french on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1362
• Wer: 0.1225

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: 5e-05
• 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: 100
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1934	0.4329	100	0.1429	0.1356
0.2189	0.8658	200	0.1358	0.1362
0.2127	1.2987	300	0.1262	0.1336
0.1927	1.7316	400	0.1344	0.1324
0.1808	2.1645	500	0.1275	0.1288
0.1675	2.5974	600	0.1307	0.1264
0.1392	3.0303	700	0.1329	0.1261
0.1539	3.4632	800	0.1356	0.1220
0.1478	3.8961	900	0.1384	0.1243
0.1372	4.3290	1000	0.1320	0.1217
0.147	4.7619	1100	0.1362	0.1225

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1