mascir_fr_hubert_test

This model is a fine-tuned version of facebook/hubert-large-ls960-ft on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0113
• Wer: 0.1680

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	3.0885	0.9919
5.8634	16.13	500	2.8476	0.9919
5.8634	24.19	750	1.1091	0.9461
1.7302	32.26	1000	0.4035	0.6076
1.7302	40.32	1250	0.1643	0.3980
0.5446	48.39	1500	0.0872	0.2784
0.5446	56.45	1750	0.0464	0.2257
0.3144	64.52	2000	0.0311	0.2021
0.3144	72.58	2250	0.0213	0.1891
0.2224	80.65	2500	0.0155	0.1816
0.2224	88.71	2750	0.0132	0.1699
0.1871	96.77	3000	0.0113	0.1680

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.0
• Tokenizers 0.13.3