Zum Inhalt springen
ModelAufgelistetExtern
Herunterladen

Whisper Tiny Khmer

This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set: Loss: 0.0702 Cer: 21.3240

ArtText modelBasismodellopenai/whisper-tinyVersionBBewertung

Modellquelle

Art
Text model
Dateigröße
38,6 MB
Basismodell
openai/whisper-tiny
Version
vmodel
Aktualisiert
31. Okt. 2026
Downloads
24
Quelle
Hugging Face

Quellenbeschreibung

whisper-tiny-khmer

This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0702
  • Cer: 21.3240

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: 3.75e-05
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • 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: linear
  • lr_scheduler_warmup_steps: 200
  • training_steps: 3000
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossCer
0.67460.48475000.320044.1463
0.25460.969510000.128027.2033
0.16391.453715000.096523.0473
0.15591.938420000.081521.5974
0.10562.422725000.074421.2300
0.10342.907430000.070221.3240

Framework versions

  • Transformers 5.14.1
  • Pytorch 2.8.0+cu128
  • Datasets 5.0.0
  • Tokenizers 0.22.2

Quellen

1 Quelle
Hugging FacePrimärVersion ae07f84498c126f6b5d75fda546c734e75a14ddc
huggingface.co/sengtha/whisper-tiny-khmer/tree/ae07f84498c126f6b5d75fda546c734e75a14ddc

Verifiziert 31. Okt.

Download files

Modellartefakte

1 Artefakt

ct2/model.bin

bin · 38,6 MB · SHA-256 0e3319f974ac…d66a · Hugging Face

Download file

Quellenauszüge

3 Auszüge

--- library_name: transformers license: apache-2.0 base_model: openai/whisper-tiny tags: - generated_from_trainer model-index: - name: whisper-tiny-khmer 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-tiny-khmer This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0702 - Cer: 21.3240 ## 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: 3.75e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - 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: linear - lr_scheduler_warmup_steps: 200 - training_steps: 3000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Cer | |:-------------:|:------:|:----:|:---------------:|:-------:| | 0.6746 | 0.4847 | 500 | 0.3200 | 44.1463 | | 0.2546 | 0.9695 | 1000 | 0.1280 | 27.2033 | | 0.1639 | 1.4537 | 1500 | 0.0965 | 23.0473 | | 0.1559 | 1.9384 | 2000 | 0.0815 | 21.5974 | | 0.1056 | 2.4227 | 2500 | 0.0744 | 21.2300 | | 0.1034 | 2.9074 | 3000 | 0.0702 | 21.3240 | ### Framework versions - Transformers 5.14.1 - Pytorch 2.8.0+cu128 - Datasets 5.0.0 - Tokenizers 0.22.2

Source context: 24 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo sengtha/whisper-tiny-khmer

Source context: 283 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo sengtha/whisper-tiny-khmer