wav2vec2-large-mms-1b-swahili_v2

This model is a fine-tuned version of facebook/mms-1b-all on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:

• eval_loss: inf
• eval_wer: 0.2173
• eval_runtime: 57.2449
• eval_samples_per_second: 34.938
• eval_steps_per_second: 4.367
• epoch: 0.64
• step: 800

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: 8
• 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
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.40.0.dev0
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2