bambara-10-hours-bambara-asr-hf

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.6353
• eval_wer: 0.4848
• eval_cer: 0.2216
• eval_runtime: 142.6245
• eval_samples_per_second: 43.141
• eval_steps_per_second: 2.699
• epoch: 41.93
• step: 14800

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 16
• 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: 50

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.0+cu118
• Datasets 2.17.0
• Tokenizers 0.15.2