saq-20s_asr-scr_w2v2-base_001

This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.6013
• eval_per: 0.1403
• eval_pcc: 0.6666
• eval_ctc_loss: 0.4803
• eval_mse_loss: 0.8934
• eval_runtime: 180.2975
• eval_samples_per_second: 8.275
• eval_steps_per_second: 8.275
• epoch: 11.0
• step: 8162

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: 16
• eval_batch_size: 1
• seed: 1111
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2226
• training_steps: 22260
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.38.1
• Pytorch 2.0.1
• Datasets 2.16.1
• Tokenizers 0.15.2