Skip to content
ModelListedExternal
Download

Whisper Small Malagasy

This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.8951 Wer: 0.4742

KindText modelBase modelopenai/whisper-smallVersionFP32Bgrade

Model source

Kind
Text model
File size
922 MB
Base model
openai/whisper-small
Version
vFP32
Updated
Oct 31, 2026
Downloads
10
Source
Hugging Face

Source description

wisper-small-malagasy

This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8951
  • Wer: 0.4742

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
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Use 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: 500
  • training_steps: 5000
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossWer
1.39048.19835000.64570.4847
0.028516.396710000.75990.4859
0.003824.595015000.78530.4771
0.000832.793420000.82250.4738
0.000340.991725000.84410.4738
0.000249.181830000.86170.4754
0.000257.380235000.87510.4758
0.000265.578540000.88570.4746
0.000173.776945000.89220.4734
0.000181.975250000.89510.4742

Framework versions

  • Transformers 4.53.2
  • Pytorch 2.6.0+cu124
  • Datasets 2.18.0
  • Tokenizers 0.21.2

Sources

1 source
Hugging FacePrimaryVersion 0becd781c5dc4aecb43af861ff7170d9af0ce1b1
huggingface.co/HobyTahiry/whisper-small-malagasy/tree/0becd781c5dc4aecb43af861ff7170d9af0ce1b1

Verified Oct 31

Download files

Model artifacts

1 artifact

model.safetensors

safetensors · FP32 (unverified) · 922 MB · SHA-256 f0a71ebb3b02…9fb3 · Hugging Face

Download file

Source excerpts

3 excerpts

--- library_name: transformers license: cc-by-nc-sa-4.0 base_model: openai/whisper-small tags: - generated_from_trainer metrics: - wer model-index: - name: wisper-small-malagasy 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. --> # wisper-small-malagasy This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.8951 - Wer: 0.4742 ## 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 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Use 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: 500 - training_steps: 5000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-------:|:----:|:---------------:|:------:| | 1.3904 | 8.1983 | 500 | 0.6457 | 0.4847 | | 0.0285 | 16.3967 | 1000 | 0.7599 | 0.4859 | | 0.0038 | 24.5950 | 1500 | 0.7853 | 0.4771 | | 0.0008 | 32.7934 | 2000 | 0.8225 | 0.4738 | | 0.0003 | 40.9917 | 2500 | 0.8441 | 0.4738 | | 0.0002 | 49.1818 | 3000 | 0.8617 | 0.4754 | | 0.0002 | 57.3802 | 3500 | 0.8751 | 0.4758 | | 0.0002 | 65.5785 | 4000 | 0.8857 | 0.4746 | | 0.0001 | 73.7769 | 4500 | 0.8922 | 0.4734 | | 0.0001 | 81.9752 | 5000 | 0.8951 | 0.4742 | ### Framework versions - Transformers 4.53.2 - Pytorch 2.6.0+cu124 - Datasets 2.18.0 - Tokenizers 0.21.2

Source context: 10 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo HobyTahiry/whisper-small-malagasy

Source context: 14 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo HobyTahiry/whisper-small-malagasy