wav2vec2-common_voice-vi-demo

This model is a fine-tuned version of ylacombe/w2v-bert-2.0 on the MOZILLA-FOUNDATION/COMMON_VOICE_16_0 - VI dataset. It achieves the following results on the evaluation set:

• Loss: 3.3958
• Wer: 1.0

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: 0.002
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 15.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	2.26	200	3.5924	1.0
No log	4.52	400	3.4946	1.0
5.7152	6.78	600	3.4630	1.0
5.7152	9.04	800	3.4525	1.0
3.5048	11.3	1000	3.4329	1.0
3.5048	13.56	1200	3.4074	1.0

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.14.5
• Tokenizers 0.15.0