| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: facebook/wav2vec2-base-960h |
| tags: |
| - generated_from_trainer |
| metrics: |
| - wer |
| model-index: |
| - name: Wav2vec2_Single_Utt_Test_Two |
| results: [] |
| --- |
| |
| <!-- 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_Single_Utt_Test_Two |
|
|
| This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 1.4727 |
| - Wer: 1.0 |
|
|
| ## 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: 12 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - gradient_accumulation_steps: 2 |
| - total_train_batch_size: 24 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_steps: 500 |
| - num_epochs: 10 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Wer | |
| |:-------------:|:------:|:----:|:---------------:|:---:| |
| | 1.8088 | 3.2051 | 1000 | 1.4820 | 1.0 | |
| | 2.6287 | 6.4103 | 2000 | 0.9560 | 1.0 | |
| | 1.2689 | 9.6154 | 3000 | 0.9546 | 1.0 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.57.1 |
| - Pytorch 2.8.0+cu128 |
| - Datasets 4.3.0 |
| - Tokenizers 0.22.1 |
| |
