seamless_m4t_v2_fleurs_fleurs_49370_trial

This model is a fine-tuned version of facebook/seamless-m4t-v2-large on the fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 0.3845
• Global Wer: 15.5547

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-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Global Wer
9.9701	0.0945	50	1.2403	23.9560
5.9001	0.1890	100	2.1859	83.0402
2.7968	0.2836	150	1.0900	28.1026
0.9012	0.3781	200	0.5424	18.8071
0.7783	0.4726	250	0.4588	17.5494
0.5567	0.5671	300	0.4257	16.9598
0.5072	0.6616	350	0.4079	16.6356
0.4836	0.7561	400	0.3993	16.2916
0.4805	0.8507	450	0.3911	15.5252
0.4641	0.9452	500	0.3845	15.5547

Framework versions

• Transformers 5.0.0.dev0
• Pytorch 2.9.0+cu126
• Datasets 3.6.0
• Tokenizers 0.22.2