Aller au contenu
ModelPrésentéExterne
Télécharger

Whisper Small Finetuned Iwslt Irish Welsh Curriculum B

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set: Loss: 4.7344 Wer: 104.2103 Bleu: 3.1336 Chrf++: 18.6533 Comet: 0.4427

Sourcehuggingface.co/jjnhuang/whisper-small-finetuned-iwslt-irish-welsh-curriculum-b/tree/b9ad1f5102152772e8db2ed5eeb6eaa1edfa4ddd
TypeText modelModèle de baseopenai/whisper-smallVersionBClasse

Source du modèle

Type
Text model
Taille du fichier
922 MB
Modèle de base
openai/whisper-small
Version
vFP32
Mis à jour
31 oct. 2026
Téléchargements
8
Source
Hugging Face

Description de la source

whisper-small-finetuned-iwslt-irish-welsh-curriculum-b

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 4.7344
  • Wer: 104.2103
  • Bleu: 3.1336
  • Chrf++: 18.6533
  • Comet: 0.4427

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: 5e-05
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.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_steps: 1000
  • training_steps: 5000
  • mixed_precision_training: Native AMP
  • label_smoothing_factor: 0.1

Training results

Training LossEpochStepValidation LossWerBleuChrf++Comet
2.47562.670912504.3221112.73942.396017.97120.4415
1.66845.341925004.4973105.99022.887218.81110.4461
1.54948.012837504.6734104.05672.991918.62360.4477
1.48510.683850004.7344104.21033.133618.65330.4427

Framework versions

  • Transformers 4.52.0
  • Pytorch 2.12.1+cu130
  • Datasets 2.21.0
  • Tokenizers 0.21.4

Sources

1 source
Hugging FacePrincipalVersion b9ad1f5102152772e8db2ed5eeb6eaa1edfa4ddd
huggingface.co/jjnhuang/whisper-small-finetuned-iwslt-irish-welsh-curriculum-b/tree/b9ad1f5102152772e8db2ed5eeb6eaa1edfa4ddd

Vérifié 31 oct.

Download files

Repository files

File inventory only; completeness is unverified.

Artefacts du modèle

2 artefacts

last-checkpoint/model.safetensors

safetensors · FP32 (unverified) · 922 MB · SHA-256 a508f81a564d…3509 · Hugging Face

Download file

model.safetensors

safetensors · FP32 (unverified) · 922 MB · SHA-256 a508f81a564d…3509 · Hugging Face

Download file

Extraits de sources

3 extraits
Readme15 aoûthuggingface.co/jjnhuang/whisper-small-finetuned-iwslt-irish-welsh-curriculum-b

--- library_name: transformers license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer metrics: - wer - bleu model-index: - name: whisper-small-finetuned-iwslt-irish-welsh-curriculum-b 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. --> # whisper-small-finetuned-iwslt-irish-welsh-curriculum-b This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset. It achieves the following results on the evaluation set: - Loss: 4.7344 - Wer: 104.2103 - Bleu: 3.1336 - Chrf++: 18.6533 - Comet: 0.4427 ## 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: 5e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Use OptimizerNames.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_steps: 1000 - training_steps: 5000 - mixed_precision_training: Native AMP - label_smoothing_factor: 0.1 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | Bleu | Chrf++ | Comet | |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:-------:|:------:| | 2.4756 | 2.6709 | 1250 | 4.3221 | 112.7394 | 2.3960 | 17.9712 | 0.4415 | | 1.6684 | 5.3419 | 2500 | 4.4973 | 105.9902 | 2.8872 | 18.8111 | 0.4461 | | 1.5494 | 8.0128 | 3750 | 4.6734 | 104.0567 | 2.9919 | 18.6236 | 0.4477 | | 1.485 | 10.6838 | 5000 | 4.7344 | 104.2103 | 3.1336 | 18.6533 | 0.4427 | ### Framework versions - Transformers 4.52.0 - Pytorch 2.12.1+cu130 - Datasets 2.21.0 - Tokenizers 0.21.4

Note31 oct.huggingface.co/jjnhuang/whisper-small-finetuned-iwslt-irish-welsh-curriculum-b

Source context: 8 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo jjnhuang/whisper-small-finetuned-iwslt-irish-welsh-curriculum-b

Note15 aoûthuggingface.co/jjnhuang/whisper-small-finetuned-iwslt-irish-welsh-curriculum-b

Source context: 36 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo jjnhuang/whisper-small-finetuned-iwslt-irish-welsh-curriculum-b