Skip to content
ModelListedExternal
Download

Whisper Small Finetuned Iwslt Irish Welsh Curriculum 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: 3.4795 Wer: 93.8291 Bleu: 7.4317 Chrf++: 27.4259 Comet: 0.5182

Sourcehuggingface.co/jjnhuang/whisper-small-finetuned-iwslt-irish-welsh-curriculum-synthetic/tree/d698cbcd030ca66788d326e683d7984a17fdcb0c
KindText modelBase modelopenai/whisper-smallVersionCgrade

Model source

Kind
Text model
File size
922 MB
Base model
openai/whisper-small
Version
vmodel
Updated
Sep 27, 2026
Downloads
4
Source
Hugging Face

Source description

whisper-small-finetuned-iwslt-irish-welsh-curriculum-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: 3.4795
  • Wer: 93.8291
  • Bleu: 7.4317
  • Chrf++: 27.4259
  • Comet: 0.5182

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
2.29720.426425003.6835140.08852.838620.01150.4674
2.06710.852850003.5530127.00584.040122.71340.4854
2.25361.279275003.4554110.17355.947525.91640.5103
2.09541.7056100003.435799.09657.424526.94930.5168
2.09352.1320125003.454097.42506.960926.83700.5199
2.03052.5584150003.479593.82917.431727.42590.5182

Framework versions

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

Sources

1 source
Hugging FacePrimaryVersion d698cbcd030ca66788d326e683d7984a17fdcb0c
huggingface.co/jjnhuang/whisper-small-finetuned-iwslt-irish-welsh-curriculum-synthetic/tree/d698cbcd030ca66788d326e683d7984a17fdcb0c

Verified Aug 30

Download files

Model artifacts

2 artifacts

last-checkpoint/model.safetensors

safetensors · 922 MB · SHA-256 827078413fac…78f0 · Hugging Face

Download file

model.safetensors

safetensors · 922 MB · SHA-256 827078413fac…78f0 · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeAug 30huggingface.co/jjnhuang/whisper-small-finetuned-iwslt-irish-welsh-curriculum-synthetic

--- 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-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-curriculum-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: 3.4795 - Wer: 93.8291 - Bleu: 7.4317 - Chrf++: 27.4259 - Comet: 0.5182 ## 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 | |:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|:-------:|:------:| | 2.2972 | 0.4264 | 2500 | 3.6835 | 140.0885 | 2.8386 | 20.0115 | 0.4674 | | 2.0671 | 0.8528 | 5000 | 3.5530 | 127.0058 | 4.0401 | 22.7134 | 0.4854 | | 2.2536 | 1.2792 | 7500 | 3.4554 | 110.1735 | 5.9475 | 25.9164 | 0.5103 | | 2.0954 | 1.7056 | 10000 | 3.4357 | 99.0965 | 7.4245 | 26.9493 | 0.5168 | | 2.0935 | 2.1320 | 12500 | 3.4540 | 97.4250 | 6.9609 | 26.8370 | 0.5199 | | 2.0305 | 2.5584 | 15000 | 3.4795 | 93.8291 | 7.4317 | 27.4259 | 0.5182 | ### Framework versions - Transformers 4.52.0 - Pytorch 2.12.1+cu130 - Datasets 2.21.0 - Tokenizers 0.21.4

NoteAug 30huggingface.co/jjnhuang/whisper-small-finetuned-iwslt-irish-welsh-curriculum-synthetic

Source context: 4 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo jjnhuang/whisper-small-finetuned-iwslt-irish-welsh-curriculum-synthetic