| | --- |
| | license: apache-2.0 |
| | tags: |
| | - generated_from_trainer |
| | - hf-asr-leaderboard |
| | - whisper-event |
| | metrics: |
| | - wer |
| | base_model: openai/whisper-medium |
| | model-index: |
| | - name: openai/whisper-medium |
| | results: |
| | - task: |
| | type: automatic-speech-recognition |
| | name: Automatic Speech Recognition |
| | dataset: |
| | name: mozilla-foundation/common_voice_11_0 ca |
| | type: mozilla-foundation/common_voice_11_0 |
| | args: 'config: ml, split: test' |
| | metrics: |
| | - type: wer |
| | value: 8.282966640983934 |
| | name: Wer |
| | --- |
| | |
| | <!-- 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. --> |
| |
|
| | # openai/whisper-medium |
| |
|
| | This is an automatic speech recognition model that also does punctuation and casing. This model is for research only, **we do not recommend using this model on production environments**. See our [learnings](https://huggingface.co/softcatala/whisper-small-ca/blob/main/TRAINING.md) when training these models. |
| |
|
| |
|
| | This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the mozilla-foundation/common_voice_11_0 ca dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.2029 |
| | - Wer: 8.3235 |
| | |
| | ## 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: 1e-05 |
| | - train_batch_size: 2 |
| | - eval_batch_size: 1 |
| | - seed: 42 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: linear |
| | - lr_scheduler_warmup_steps: 500 |
| | - training_steps: 20000 |
| | - mixed_precision_training: Native AMP |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | Wer | |
| | |:-------------:|:-----:|:-----:|:---------------:|:-------:| |
| | | 0.2652 | 0.1 | 2000 | 0.3469 | 15.3537 | |
| | | 0.3273 | 0.2 | 4000 | 0.3151 | 14.1141 | |
| | | 0.2696 | 0.3 | 6000 | 0.2955 | 13.2472 | |
| | | 0.1725 | 0.4 | 8000 | 0.2787 | 11.6834 | |
| | | 0.1741 | 0.5 | 10000 | 0.2648 | 11.0088 | |
| | | 0.2037 | 0.6 | 12000 | 0.2470 | 10.1909 | |
| | | 0.1586 | 0.7 | 14000 | 0.2333 | 9.4096 | |
| | | 0.1548 | 0.8 | 16000 | 0.2184 | 8.9724 | |
| | | 0.1799 | 1.08 | 18000 | 0.2064 | 8.2830 | |
| | | 0.1165 | 1.18 | 20000 | 0.2029 | 8.3235 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.25.1 |
| | - Pytorch 1.10.0+cu102 |
| | - Datasets 2.7.1 |
| | - Tokenizers 0.13.2 |
| |
|
