wav2vec2-common_voice-tr-mms-demo

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

• Loss: 0.1532
• Wer: 0.2267

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: 0.001
• train_batch_size: 32
• 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: 4.0

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0.92	100	0.1822	0.2605
No log	1.83	200	0.1620	0.2389
No log	2.75	300	0.1581	0.2318
No log	3.67	400	0.1535	0.2270

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.12.0
• Tokenizers 0.13.3