wav2vec2-base-mn-scratch

This model is a fine-tuned version of bayartsogt/wav2vec2-base-mn-pretrain-42h on the common_voice dataset. It achieves the following results on the evaluation set:

• eval_loss: 2.8294
• eval_wer: 1.0026
• eval_cer: 0.7258
• eval_runtime: 173.2914
• eval_samples_per_second: 10.883
• eval_steps_per_second: 1.362
• epoch: 28.57
• step: 3600

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: 2e-05
• 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
• training_steps: 10000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0
• Datasets 2.1.0
• Tokenizers 0.12.1