Aller au contenu
ModelPrésentéExterne
Télécharger

Cali Whisper Tiny.en Drop 004 Production

This model is a fine-tuned version of openai/whisper-tiny on the cali-name-dataset-short-version dataset. It achieves the following results on the evaluation set: Loss: 0.0001 Wer Ortho: 0.0 Wer: 0.0

Sourcehuggingface.co/1Developer/cali-whisper-tiny.en-drop-004-production/tree/770b6388da831976c9c1fe25faf3c1ac4a7a2b36
TypeText modelModèle de baseopenai/whisper-tinyVersionmodelBClasse

Source du modèle

Type
Text model
Taille du fichier
144 MB
Modèle de base
openai/whisper-tiny
Version
vmodel
Mis à jour
26 sept. 2026
Téléchargements
29
Source
Hugging Face

Description de la source

whisper-tiny-calista-basics-v10

This model is a fine-tuned version of openai/whisper-tiny on the cali-name-dataset-short-version dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0001
  • Wer Ortho: 0.0
  • Wer: 0.0

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: 1e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: constant_with_warmup
  • lr_scheduler_warmup_steps: 50
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossWer OrthoWer
No log0.3509204.300987.121238.6364
5.08210.7018400.238910.60619.8485
0.95791.0526600.00180.00.0
0.01591.4035800.00070.00.0
0.00061.75441000.00050.00.0
0.00062.10531200.00030.00.0
0.00012.45611400.00020.00.0
0.00012.80701600.00020.00.0
0.00813.15791800.00040.00.0
0.00023.50882000.00020.00.0
0.00023.85962200.00030.00.0
0.00394.21052400.00020.00.0
0.00084.56142600.00010.00.0
0.00004.91232800.00010.00.0
0.00005.26323000.00010.00.0
0.00005.61403200.00010.00.0
0.00005.96493400.00300.00.0
0.00216.31583600.00010.00.0
0.00006.66673800.00010.00.0
0.00497.01754000.00010.00.0
0.00497.36844200.00020.00.0
0.00057.71934400.00020.00.0
0.00008.07024600.00010.00.0
0.00008.42114800.00010.00.0
0.00008.77195000.00010.00.0

Framework versions

  • Transformers 5.12.1
  • Pytorch 2.11.0+cu128
  • Datasets 5.0.0
  • Tokenizers 0.22.2

Sources

1 source
Hugging FacePrincipalVersion 770b6388da831976c9c1fe25faf3c1ac4a7a2b36
huggingface.co/1Developer/cali-whisper-tiny.en-drop-004-production/tree/770b6388da831976c9c1fe25faf3c1ac4a7a2b36

Vérifié 6 sept.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 144 MB · SHA-256 11a838f9db41…72bf · Hugging Face

Télécharger

Extraits de sources

2 extraits
Readme6 sept.huggingface.co/1Developer/cali-whisper-tiny.en-drop-004-production

--- library_name: transformers language: - en license: apache-2.0 base_model: openai/whisper-tiny tags: - generated_from_trainer datasets: - openai/whisper-tiny metrics: - wer model-index: - name: whisper-tiny-calista-basics-v10 results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: cali-name-dataset-short-version type: openai/whisper-tiny config: default split: test args: default metrics: - name: Wer type: wer value: 0.0 --- <!-- 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-tiny-calista-basics-v10 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the cali-name-dataset-short-version dataset. It achieves the following results on the evaluation set: - Loss: 0.0001 - Wer Ortho: 0.0 - Wer: 0.0 ## 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: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: constant_with_warmup - lr_scheduler_warmup_steps: 50 - training_steps: 500 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer | |:-------------:|:------:|:----:|:---------------:|:---------:|:-------:| | No log | 0.3509 | 20 | 4.3009 | 87.1212 | 38.6364 | | 5.0821 | 0.7018 | 40 | 0.2389 | 10.6061 | 9.8485 | | 0.9579 | 1.0526 | 60 | 0.0018 | 0.0 | 0.0 | | 0.0159 | 1.4035 | 80 | 0.0007 | 0.0 | 0.0 | | 0.0006 | 1.7544 | 100 | 0.0005 | 0.0 | 0.0 | | 0.0006 | 2.1053 | 120 | 0.0003 | 0.0 | 0.0 | | 0.0001 | 2.4561 | 140 | 0.0002 | 0.0 | 0.0 | | 0.0001 | 2.8070 | 160 | 0.0002 | 0.0 | 0.0 | | 0.0081 | 3.1579 | 180 | 0.0004 | 0.0 | 0.0 | | 0.0002 | 3.5088 | 200 | 0.0002 | 0.0 | 0.0 | | 0.0002 | 3.8596 | 220 | 0.0003 | 0.0 | 0.0 | | 0.0039 | 4.2105 | 240 | 0.0002 | 0.0 | 0.0 | | 0.0008 | 4.5614 | 260 | 0.0001 | 0.0 | 0.0 | | 0.0000 |...

Note6 sept.huggingface.co/1Developer/cali-whisper-tiny.en-drop-004-production

Source context: 29 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo 1Developer/cali-whisper-tiny.en-drop-004-production