| library_name: peft | |
| language: | |
| - en | |
| license: apache-2.0 | |
| base_model: openai/whisper-tiny | |
| tags: | |
| - wft | |
| - whisper | |
| - automatic-speech-recognition | |
| - audio | |
| - speech | |
| - generated_from_trainer | |
| datasets: | |
| - hf-internal-testing/librispeech_asr_dummy | |
| model-index: | |
| - name: wft-test-model | |
| 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. --> | |
| # wft-test-model | |
| This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the hf-internal-testing/librispeech_asr_dummy dataset. | |
| It achieves the following results on the evaluation set: | |
| - eval_loss: 0.6337 | |
| - eval_wer: 40.9449 | |
| - eval_cer: 73.7926 | |
| - eval_decode_time: 0.5137 | |
| - eval_wer_time: 0.0217 | |
| - eval_cer_time: 0.0030 | |
| - eval_runtime: 1.3876 | |
| - eval_samples_per_second: 7.207 | |
| - eval_steps_per_second: 1.441 | |
| - epoch: 2.02 | |
| - step: 40 | |
| ## 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: 0.0005 | |
| - train_batch_size: 4 | |
| - 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: 50 | |
| - training_steps: 100 | |
| ### Framework versions | |
| - PEFT 0.13.2 | |
| - Transformers 4.45.2 | |
| - Pytorch 2.5.0 | |
| - Datasets 3.0.2 | |
| - Tokenizers 0.20.1 |