JacobLinCool/wft-test-model

1---2library_name: peft3language:4- en5license: apache-2.06base_model: openai/whisper-tiny7tags:8- wft9- whisper10- automatic-speech-recognition11- audio12- speech13- generated_from_trainer14datasets:15- hf-internal-testing/librispeech_asr_dummy16metrics:17- wer18model-index:19- name: wft-test-model20  results:21  - task:22      type: automatic-speech-recognition23      name: Automatic Speech Recognition24    dataset:25      name: hf-internal-testing/librispeech_asr_dummy26      type: hf-internal-testing/librispeech_asr_dummy27    metrics:28    - type: wer29      value: 5.90551181102362230      name: Wer31---32 33<!-- This model card has been generated automatically according to the information the Trainer had access to. You34should probably proofread and complete it, then remove this comment. -->35 36# wft-test-model37 38This 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.39It achieves the following results on the evaluation set:40- Loss: 0.118541- Wer: 5.905542- Cer: 83.238643- Decode Time: 0.529944- Wer Time: 0.004745- Cer Time: 0.003046 47## Model description48 49More information needed50 51## Intended uses & limitations52 53More information needed54 55## Training and evaluation data56 57More information needed58 59## Training procedure60 61### Training hyperparameters62 63The following hyperparameters were used during training:64- learning_rate: 0.000565- train_batch_size: 466- eval_batch_size: 867- seed: 4268- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0869- lr_scheduler_type: linear70- lr_scheduler_warmup_steps: 5071- training_steps: 10072 73### Training results74 75| Training Loss | Epoch | Step | Validation Loss | Wer      | Cer      | Decode Time | Wer Time | Cer Time |76|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|:--------:|:--------:|77| 2.4079        | 0.1   | 10   | 1.9885          | 312.2047 | 119.2472 | 0.5334      | 0.0169   | 0.0041   |78| 1.2303        | 1.01  | 20   | 1.1646          | 258.2677 | 100.0    | 0.5213      | 1.4057   | 0.0046   |79| 0.8667        | 1.11  | 30   | 0.8100          | 37.7953  | 52.3438  | 0.5008      | 0.0396   | 0.0045   |80| 0.4517        | 2.02  | 40   | 0.6337          | 40.9449  | 73.7926  | 0.5137      | 0.0217   | 0.0030   |81| 0.4352        | 2.12  | 50   | 0.4493          | 16.5354  | 88.1392  | 0.5203      | 0.0054   | 0.0032   |82| 0.2341        | 3.03  | 60   | 0.2922          | 8.2677   | 97.5852  | 0.5434      | 0.0060   | 0.0032   |83| 0.2233        | 3.13  | 70   | 0.2026          | 9.0551   | 83.5227  | 0.5359      | 0.0063   | 0.0033   |84| 0.1098        | 4.04  | 80   | 0.1665          | 5.9055   | 83.9489  | 0.5316      | 0.0056   | 0.0029   |85| 0.0678        | 4.14  | 90   | 0.1279          | 7.0866   | 81.1080  | 0.5388      | 0.0079   | 0.0038   |86| 0.078         | 5.05  | 100  | 0.1185          | 5.9055   | 83.2386  | 0.5299      | 0.0047   | 0.0030   |87 88 89### Framework versions90 91- PEFT 0.13.292- Transformers 4.45.293- Pytorch 2.5.094- Datasets 3.0.295- Tokenizers 0.20.1