Wav2Vec2ForSequenceClassification-finetuned-eos_poc5_ge-di-v7-meeting-v2

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

• Loss: 0.6822
• Accuracy: 0.6114

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: 3e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.5858	0.9748	29	0.6455	0.6517
2.5709	1.9748	58	0.6422	0.6517
2.5285	2.9748	87	0.6421	0.6517
2.4906	3.9748	116	0.6335	0.6540
2.437	4.9748	145	0.6330	0.6517
2.3735	5.9748	174	0.6458	0.5972
2.1678	6.9748	203	0.6553	0.6114
2.1317	7.9748	232	0.6734	0.5900
2.0619	8.9748	261	0.6809	0.5806
1.9324	9.9748	290	0.6822	0.6114

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0