Saltar al contenido
ModelPublicadoExterno
Descargar

Whisper Small Finetuned Iwslt Irish Transfer Welsh 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: 6.7416 Wer: 105.8005 Bleu: 0.6736 Chrf++: 12.5667 Comet: 0.4173

TipoText modelModelo baseopenai/whisper-smallVersiónCcalidad

Fuente del modelo

Tipo
Text model
Tamaño del archivo
922 MB
Modelo base
openai/whisper-small
Versión
vmodel
Actualizado
26 sept 2026
Descargas
8
Fuente
Hugging Face

Descripción de la fuente

whisper-small-finetuned-iwslt-irish-transfer-welsh-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: 6.7416
  • Wer: 105.8005
  • Bleu: 0.6736
  • Chrf++: 12.5667
  • Comet: 0.4173

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
1.8872.670912505.9918111.16730.963813.37800.4054
1.50065.341925006.3732103.90310.776812.27730.4111
1.46118.012837506.4941103.60500.753312.28200.4108
1.42310.683850006.7416105.80050.673612.56670.4173

Framework versions

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

Fuentes

1 fuente

Download files

Artefactos del modelo

2 artefactos

last-checkpoint/model.safetensors

safetensors · 922 MB · SHA-256 2713065b10b0…2ceb · Hugging Face

Download file

model.safetensors

safetensors · 922 MB · SHA-256 2713065b10b0…2ceb · Hugging Face

Download file

Extractos de fuentes

2 extractos

--- 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-transfer-welsh-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-transfer-welsh-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: 6.7416 - Wer: 105.8005 - Bleu: 0.6736 - Chrf++: 12.5667 - Comet: 0.4173 ## 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 | |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:-------:|:------:| | 1.887 | 2.6709 | 1250 | 5.9918 | 111.1673 | 0.9638 | 13.3780 | 0.4054 | | 1.5006 | 5.3419 | 2500 | 6.3732 | 103.9031 | 0.7768 | 12.2773 | 0.4111 | | 1.4611 | 8.0128 | 3750 | 6.4941 | 103.6050 | 0.7533 | 12.2820 | 0.4108 | | 1.423 | 10.6838 | 5000 | 6.7416 | 105.8005 | 0.6736 | 12.5667 | 0.4173 | ### Framework versions - Transformers 4.52.0 - Pytorch 2.12.1+cu130 - Datasets 2.21.0 - Tokenizers 0.21.4

Source context: 8 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo jjnhuang/whisper-small-finetuned-iwslt-irish-transfer-welsh-no-frozen-decoder