Skip to content
ModelListedExternal
Download

Whisper Small Finetuned Iwslt Irish No Frozen Decoder

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: 6.4202 Wer: 103.9664 Bleu: 0.7147 Chrf++: 12.6295 Comet: 0.4187

Sourcehuggingface.co/jjnhuang/whisper-small-finetuned-iwslt-irish-no-frozen-decoder/tree/0d8a26968877160156935e4bed5683f011cf9622
KindText modelBase modelopenai/whisper-smallVersion

Model source

Kind
Text model
File size
922 MB
Base model
openai/whisper-small
Version
vmodel
Updated
Sep 22, 2026
Downloads
5
Source
Hugging Face

Source description

whisper-small-finetuned-iwslt-irish-no-frozen-decoder

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: 6.4202
  • Wer: 103.9664
  • Bleu: 0.7147
  • Chrf++: 12.6295
  • Comet: 0.4187

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
1.72982.670912505.2277102.93640.843912.82270.4084
1.50095.341925005.7399103.30680.781312.93510.4124
1.46078.012837506.0951103.46950.686812.53950.4161
1.42210.683850006.4202103.96640.714712.62950.4187

Framework versions

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

Sources

1 source
Hugging FacePrimaryVersion 0d8a26968877160156935e4bed5683f011cf9622
huggingface.co/jjnhuang/whisper-small-finetuned-iwslt-irish-no-frozen-decoder/tree/0d8a26968877160156935e4bed5683f011cf9622

Verified Sep 22

Model artifacts

2 artifacts

last-checkpoint/model.safetensors

safetensors · 922 MB · SHA-256 3294c6dbd67a…5a75 · Hugging Face

Download

model.safetensors

safetensors · 922 MB · SHA-256 3294c6dbd67a…5a75 · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 22huggingface.co/jjnhuang/whisper-small-finetuned-iwslt-irish-no-frozen-decoder

--- 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-no-frozen-decoder 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-no-frozen-decoder 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: 6.4202 - Wer: 103.9664 - Bleu: 0.7147 - Chrf++: 12.6295 - Comet: 0.4187 ## 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 | |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:-------:|:------:| | 1.7298 | 2.6709 | 1250 | 5.2277 | 102.9364 | 0.8439 | 12.8227 | 0.4084 | | 1.5009 | 5.3419 | 2500 | 5.7399 | 103.3068 | 0.7813 | 12.9351 | 0.4124 | | 1.4607 | 8.0128 | 3750 | 6.0951 | 103.4695 | 0.6868 | 12.5395 | 0.4161 | | 1.422 | 10.6838 | 5000 | 6.4202 | 103.9664 | 0.7147 | 12.6295 | 0.4187 | ### Framework versions - Transformers 4.52.0 - Pytorch 2.12.1+cu130 - Datasets 2.21.0 - Tokenizers 0.21.4

NoteSep 22huggingface.co/jjnhuang/whisper-small-finetuned-iwslt-irish-no-frozen-decoder

Source context: 5 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo jjnhuang/whisper-small-finetuned-iwslt-irish-no-frozen-decoder