Ir para o conteúdo
ModelListadosExterno
Baixar

Whisper Base Sna Cleaned

This model is a fine-tuned version of openai/whisper-base on the Cleaned Google WAXAL Shona dataset. It achieves the following results on the evaluation set: Loss: 0.4745 Wer: 38.1120

Fontehuggingface.co/CasperMuz/whisper-base-sna-cleaned/tree/81fab087117098c4dc8f0a758e7cd2cff388e786
TipoText modelModelo baseopenai/whisper-baseVersãomodelCnota

Fonte do modelo

Tipo
Text model
Tamanho do arquivo
277 MB
Modelo base
openai/whisper-base
Versão
vmodel
Atualizado
27 de set. de 2026
Downloads
8
Fonte
Hugging Face

Descrição da fonte

Whisper Medium Shona - Cleaned Data

This model is a fine-tuned version of openai/whisper-base on the Cleaned Google WAXAL Shona dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4745
  • Wer: 38.1120

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: 8
  • seed: 42
  • optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 500
  • training_steps: 10000
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.64650.59955000.661453.6187
0.45281.199010000.497943.8992
0.40461.798615000.448040.3579
0.34952.398120000.425839.6383
0.34082.997625000.408737.3055
0.26673.597130000.409337.1480
0.21964.196635000.409236.8628
0.23524.796240000.405836.4691
0.18965.395745000.414536.3957
0.19735.995250000.418736.4935
0.14766.594755000.427137.2213
0.12447.194260000.440937.1643
0.12997.793865000.443036.8112
0.11078.393370000.455837.7590
0.11838.992875000.457237.9464
0.09449.592380000.467637.7400
0.088410.191885000.470737.9464
0.087310.791490000.472538.0605
0.084311.390995000.474238.0360
0.083611.9904100000.474538.1120

Framework versions

  • Transformers 5.14.1
  • Pytorch 2.13.0+cu130
  • Datasets 5.0.1
  • Tokenizers 0.22.2

Fontes

1 fonte
Hugging FacePrimárioVersão 81fab087117098c4dc8f0a758e7cd2cff388e786
huggingface.co/CasperMuz/whisper-base-sna-cleaned/tree/81fab087117098c4dc8f0a758e7cd2cff388e786

Verificado 30 de ago.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · 277 MB · SHA-256 b3f0fe8627fd…260d · Hugging Face

Download file

Trechos de fonte

2 trechos
Readme30 de ago.huggingface.co/CasperMuz/whisper-base-sna-cleaned

--- library_name: transformers language: - sna license: apache-2.0 base_model: openai/whisper-base tags: - generated_from_trainer metrics: - wer model-index: - name: Whisper Medium Shona - Cleaned Data 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 Medium Shona - Cleaned Data This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Cleaned Google WAXAL Shona dataset. It achieves the following results on the evaluation set: - Loss: 0.4745 - Wer: 38.1120 ## 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: 8 - seed: 42 - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 500 - training_steps: 10000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-------:|:-----:|:---------------:|:-------:| | 0.6465 | 0.5995 | 500 | 0.6614 | 53.6187 | | 0.4528 | 1.1990 | 1000 | 0.4979 | 43.8992 | | 0.4046 | 1.7986 | 1500 | 0.4480 | 40.3579 | | 0.3495 | 2.3981 | 2000 | 0.4258 | 39.6383 | | 0.3408 | 2.9976 | 2500 | 0.4087 | 37.3055 | | 0.2667 | 3.5971 | 3000 | 0.4093 | 37.1480 | | 0.2196 | 4.1966 | 3500 | 0.4092 | 36.8628 | | 0.2352 | 4.7962 | 4000 | 0.4058 | 36.4691 | | 0.1896 | 5.3957 | 4500 | 0.4145 | 36.3957 | | 0.1973 | 5.9952 | 5000 | 0.4187 | 36.4935 | | 0.1476 | 6.5947 | 5500 | 0.4271 | 37.2213 | | 0.1244 | 7.1942 | 6000 | 0.4409 | 37.1643 | | 0.1299 | 7.7938 | 6500 | 0.4430 | 36.8112 | | 0.1107 | 8.3933 | 7000 | 0.4558 | 37.7590 | | 0.1183 | 8.9928 | 7500 | 0.4572 | 37.9464 | | 0.0944 | 9.5923 | 8000 | 0.4676 | 37.7400 | | 0.0884 | 10.1918 | 8500 | 0.4707 | 37.9464 | | 0.0873 | 10.7914 | 9000 | 0.4725 | 38.0605 | | 0.0843 | 11.3909 | 9500 | 0.4742 | 38.0360 | | 0.0836 | 11.9904 | 10000 | 0.4745 | 38.1120 | ### Framework versions - Transformers 5.14...

Note30 de ago.huggingface.co/CasperMuz/whisper-base-sna-cleaned

Source context: 8 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo CasperMuz/whisper-base-sna-cleaned