wav2vec2-mms-300m-ikk-3

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

wav2vec2-mms-300m-ikk-3

This model is a fine-tuned version of facebook/mms-300m on the audiofolder dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.3763
• eval_wer: 0.5580
• eval_runtime: 6.8853
• eval_samples_per_second: 14.233
• eval_steps_per_second: 1.888
• epoch: 19.59
• step: 480

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

Step Training Loss Validation Loss Wer 40 9.648200 4.719201 1.000000 80 3.953400 3.477898 1.000000 120 3.289700 3.099611 1.000000 160 3.038400 2.993551 1.000000 200 2.994500 2.979574 1.000000 240 2.959000 2.941970 1.000000 280 2.802100 2.520133 1.000000 320 1.862100 1.499739 0.746423 360 1.191800 1.336315 0.610261 400 0.951300 1.317062 0.598915 440 0.773900 1.312918 0.614702 480 0.624700 1.376327 0.557967

/usr/local/lib/python3.10/dist-packages/transformers/models/wav2vec2/processing_wav2vec2.py:156: UserWarning: as_target_processor is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument text of the regular __call__ method (either in the same call as your audio inputs, or in a separate call. warnings.warn( /usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants. warnings.warn( /usr/local/lib/python3.10/dist-packages/transformers/models/wav2vec2/processing_wav2vec2.py:156: UserWarning: as_target_processor is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument text of the regular __call__ method (either in the same call as your audio inputs, or in a separate call. warnings.warn( /usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants. warnings.warn(

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 30
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2