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
Fuente del modelo
- Tipo
- Text model
- Tamaño del archivo
- 38,6 MB
- Modelo base
- openai/whisper-tiny
- Versión
- vmodel
- Actualizado
- 31 oct 2026
- Descargas
- 24
- Fuente
- Hugging Face
Descripción de la fuente
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 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
Fuentes
1 fuente
Fuentes
1 fuenteVerificado 31 oct
Download files
Repository files
File inventory only; completeness is unverified.
- added_tokens.json
- config.json
- ct2/config.json
- ct2/model.bin
- ct2/preprocessor_config.json
- ct2/tokenizer_config.json
- ct2/vocabulary.json
- generation_config.json
- ggml-tiny-khmer-f16.bin
- ggml-tiny-khmer-q5_1.bin
- merges.txt
- model.safetensors
- normalizer.json
- onnx/config.json
- onnx/generation_config.json
- onnx/preprocessor_config.json
- preprocessor_config.json
- processor_config.json
- tokenizer.json
- tokenizer_config.json
- training_args.bin
- vocab.json
Artefactos del modelo
1 artefacto
Artefactos del modelo
1 artefactoExtractos de fuentes
3 extractos
Extractos de fuentes
3 extractos--- 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
