bambara-mms-1-hour-jeli-asr-hf

This model is a fine-tuned version of facebook/mms-1b-all on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.3954
• Wer: 0.7301
• Cer: 0.3627

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 16
• 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: 500
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
1.6441	8.0	500	1.6965	0.7606	0.3865
0.9143	16.0	1000	2.0093	0.7460	0.3704
0.5249	24.0	1500	2.2733	0.7912	0.3808
0.3111	32.0	2000	2.7380	0.7231	0.3678
0.1826	40.0	2500	3.0810	0.7323	0.3626
0.1135	48.0	3000	3.3954	0.7301	0.3627

Framework versions

• Transformers 4.45.1
• Pytorch 2.1.0+cu118
• Datasets 2.17.0
• Tokenizers 0.20.3