Zum Inhalt springen
ModelAufgelistetExtern
Herunterladen

Whisper Small Finetuned Iwslt Irish Welsh 50 50 Synthetic

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: 3.3705 Wer: 95.9162 Bleu: 8.7162 Chrf++: 29.5222 Comet: 0.5384

ArtText modelBasismodellopenai/whisper-smallVersionCBewertung

Modellquelle

Art
Text model
Dateigröße
922 MB
Basismodell
openai/whisper-small
Version
vmodel
Aktualisiert
27. Sept. 2026
Downloads
11
Quelle
Hugging Face

Quellenbeschreibung

whisper-small-finetuned-iwslt-irish-welsh-50-50-synthetic

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: 3.3705
  • Wer: 95.9162
  • Bleu: 8.7162
  • Chrf++: 29.5222
  • Comet: 0.5384

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: 15000
  • mixed_precision_training: Native AMP
  • label_smoothing_factor: 0.1

Training results

Training LossEpochStepValidation LossWerBleuChrf++Comet
2.98470.213225003.6076111.22153.933521.71130.4847
2.31540.426450003.463999.71996.309125.90060.5034
2.18070.639675003.3756103.37017.120726.94440.5208
2.09770.8528100003.365091.20899.033728.80940.5329
1.99921.0660125003.363295.93428.602329.50140.5384
1.90051.2792150003.370595.91628.716229.52220.5384

Framework versions

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

Quellen

1 Quelle
Hugging FacePrimärVersion 20203d1649d18dc5efaafd98b4d2d1ccb9353f43
huggingface.co/jjnhuang/whisper-small-finetuned-iwslt-irish-welsh-50-50-synthetic/tree/20203d1649d18dc5efaafd98b4d2d1ccb9353f43

Verifiziert 30. Aug.

Download files

Modellartefakte

2 Artefakte

last-checkpoint/model.safetensors

safetensors · 922 MB · SHA-256 58f136e76a65…d35e · Hugging Face

Download file

model.safetensors

safetensors · 922 MB · SHA-256 58f136e76a65…d35e · Hugging Face

Download file

Quellenauszüge

2 Auszüge

--- 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-50-50-synthetic 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-50-50-synthetic 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: 3.3705 - Wer: 95.9162 - Bleu: 8.7162 - Chrf++: 29.5222 - Comet: 0.5384 ## 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: 15000 - mixed_precision_training: Native AMP - label_smoothing_factor: 0.1 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | Bleu | Chrf++ | Comet | |:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|:-------:|:------:| | 2.9847 | 0.2132 | 2500 | 3.6076 | 111.2215 | 3.9335 | 21.7113 | 0.4847 | | 2.3154 | 0.4264 | 5000 | 3.4639 | 99.7199 | 6.3091 | 25.9006 | 0.5034 | | 2.1807 | 0.6396 | 7500 | 3.3756 | 103.3701 | 7.1207 | 26.9444 | 0.5208 | | 2.0977 | 0.8528 | 10000 | 3.3650 | 91.2089 | 9.0337 | 28.8094 | 0.5329 | | 1.9992 | 1.0660 | 12500 | 3.3632 | 95.9342 | 8.6023 | 29.5014 | 0.5384 | | 1.9005 | 1.2792 | 15000 | 3.3705 | 95.9162 | 8.7162 | 29.5222 | 0.5384 | ### Framework versions - Transformers 4.52.0 - Pytorch 2.12.1+cu130 - Datasets 2.21.0 - Tokenizers 0.21.4

Source context: 11 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo jjnhuang/whisper-small-finetuned-iwslt-irish-welsh-50-50-synthetic