Georgian-ASR-kaggle

This model is a fine-tuned version of facebook/mms-1b-all on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.1724
• eval_wer: 0.2415
• eval_runtime: 392.4168
• eval_samples_per_second: 6.368
• eval_steps_per_second: 0.798
• epoch: 0.0727
• step: 100

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 4
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.49.0.dev0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0