Ir para o conteúdo
ModelListadosExterno
Baixar

Whisper Large v3 Turbo Persian Audiodata2

This model is a fine-tuned version of openai/whisper-large-v3-turbo on an unknown dataset. It achieves the following results on the evaluation set: Loss: 1.1979 Wer: 42.4096

Fontehuggingface.co/tivanai2020/whisper-large-v3-turbo-persian-audiodata2/tree/9a0d262554451910a33ec8ab25b06e25d89c6c73
TipoLoRAModelo baseopenai/whisper-large-v3-turboVersãoadapter_model

Fonte do modelo

Tipo
LoRA
Tamanho do arquivo
50,0 MB
Modelo base
openai/whisper-large-v3-turbo
Versão
vadapter_model
Atualizado
14 de set. de 2026
Downloads
10
Fonte
Hugging Face

Descrição da fonte

whisper-large-v3-turbo-persian-audiodata2

This model is a fine-tuned version of openai/whisper-large-v3-turbo on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1979
  • Wer: 42.4096

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: 0.001
  • train_batch_size: 8
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • 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: cosine
  • lr_scheduler_warmup_steps: 50
  • num_epochs: 100

Training results

Training LossEpochStepValidation LossWer
2.04201.051.228044.8996
1.99902.0101.184045.0602
1.89693.0151.120043.2932
1.79664.0201.041943.7751
1.58805.0250.971642.4096
1.41816.0300.919138.8755
1.28447.0350.870536.0643
1.08768.0400.837138.0723
0.94739.0450.843741.0442
0.923210.0500.815938.7149
0.923226.0520.809138.7952
0.923227.0540.804339.3574
0.592828.0560.802940.1606
0.592829.0580.798738.3133
0.471430.0600.803837.0281
0.471431.0620.809836.3052
0.471432.0640.808336.7871
0.455533.0660.813638.7149
0.455534.0680.821739.4378
0.432835.0700.831038.6345
0.432836.0720.837137.5904
0.432837.0740.848237.9116
0.406138.0760.851037.9116
0.406139.0780.854540.0803
0.256140.0800.857740.4819
0.256141.0820.864240.8032
0.256142.0840.878239.5181
0.322443.0860.892840.9639
0.322444.0880.900241.7671
0.298245.0900.902040.6426
0.298246.0920.906142.1687
0.298247.0940.926241.4458
0.262548.0960.940141.6867
0.262549.0980.942140.1606
0.226250.01000.956443.8554
0.226251.01020.963645.7028
0.345121.01050.979540.8835
0.285422.01101.001146.1847
0.287623.01150.965042.2490
0.273324.01200.940539.9197
0.269025.01251.001741.6867
0.246126.01300.971239.0361
0.233827.01350.992739.9197
0.252028.01401.005441.8474
0.218429.01450.988140.0
0.206430.01500.991540.5622
0.195931.01551.021840.6426
0.186732.01601.050440.4819
0.177433.01651.011339.7590
0.182134.01701.035739.9197
0.156135.01751.031040.4819
0.142936.01801.066842.4096
0.130737.01851.038341.8474
0.114738.01901.079441.0442
0.110639.01951.061040.8835
0.109340.02001.093441.6867
0.098241.02051.068240.6426
0.087942.02101.083239.7590
0.085543.02151.112940.8835
0.071644.02201.106042.4096
0.079945.02251.098041.0442
0.072946.02301.116541.2048
0.069047.02351.106840.4016
0.062248.02401.106640.2410
0.060449.02451.099942.0884
0.053250.02501.107242.0884
0.050751.02551.110541.7671
0.044952.02601.112142.2490
0.040253.02651.147541.6867
0.037454.02701.163841.4458
0.036655.02751.128342.4096
0.034956.02801.147641.8474
0.033157.02851.176141.2851
0.029358.02901.168841.5261
0.031759.02951.136741.2048
0.027260.03001.156941.2048
0.026861.03051.189642.2490
0.025162.03101.166742.4900
0.024363.03151.171942.1687
0.025264.03201.188644.1767
0.024465.03251.184242.5703
0.022366.03301.177042.0080
0.021067.03351.184442.4096
0.020568.03401.182542.2490
0.020169.03451.177242.5703
0.020070.03501.182541.7671
0.020471.03551.182241.6867
0.019572.03601.188542.9719
0.019573.03651.187442.8112
0.018774.03701.184342.3293
0.018375.03751.184743.4538
0.018276.03801.190842.5703
0.017077.03851.194242.3293
0.017078.03901.190342.3293
0.017679.03951.195442.6506
0.017480.04001.191042.8112
0.017981.04051.193842.7309
0.017382.04101.197843.0522
0.016283.04151.192644.0964
0.016584.04201.194043.3735
0.017285.04251.194143.3735
0.016786.04301.194942.8916
0.016287.04351.196843.9357
0.016488.04401.196643.0522
0.016489.04451.197542.8112
0.016990.04501.199342.5703
0.016491.04551.196942.7309
0.015492.04601.197842.3293
0.015993.04651.197442.3293
0.016394.04701.199941.7671
0.016195.04751.195842.0884
0.015396.04801.197642.0884
0.016297.04851.196142.6506
0.016798.04901.198842.1687
0.015999.04951.198542.6506
0.0164100.05001.197942.4096

Framework versions

  • PEFT 0.19.1
  • Transformers 5.13.1
  • Pytorch 2.11.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.2

Fontes

1 fonte
Hugging FacePrimárioVersão 9a0d262554451910a33ec8ab25b06e25d89c6c73
huggingface.co/tivanai2020/whisper-large-v3-turbo-persian-audiodata2/tree/9a0d262554451910a33ec8ab25b06e25d89c6c73

Verificado 14 de set.

Artefatos de modelo

1 artefato

adapter_model.safetensors

safetensors · 50,0 MB · SHA-256 fc73ba7894ce…8db0 · Hugging Face

Download file

Trechos de fonte

2 trechos
Readme14 de set.huggingface.co/tivanai2020/whisper-large-v3-turbo-persian-audiodata2

--- library_name: peft license: mit base_model: openai/whisper-large-v3-turbo tags: - base_model:adapter:openai/whisper-large-v3-turbo - lora - transformers metrics: - wer model-index: - name: whisper-large-v3-turbo-persian-audiodata2 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-large-v3-turbo-persian-audiodata2 This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.1979 - Wer: 42.4096 ## 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: 0.001 - train_batch_size: 8 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 16 - 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: cosine - lr_scheduler_warmup_steps: 50 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:----:|:---------------:|:-------:| | 2.0420 | 1.0 | 5 | 1.2280 | 44.8996 | | 1.9990 | 2.0 | 10 | 1.1840 | 45.0602 | | 1.8969 | 3.0 | 15 | 1.1200 | 43.2932 | | 1.7966 | 4.0 | 20 | 1.0419 | 43.7751 | | 1.5880 | 5.0 | 25 | 0.9716 | 42.4096 | | 1.4181 | 6.0 | 30 | 0.9191 | 38.8755 | | 1.2844 | 7.0 | 35 | 0.8705 | 36.0643 | | 1.0876 | 8.0 | 40 | 0.8371 | 38.0723 | | 0.9473 | 9.0 | 45 | 0.8437 | 41.0442 | | 0.9232 | 10.0 | 50 | 0.8159 | 38.7149 | | 0.9232 | 26.0 | 52 | 0.8091 | 38.7952 | | 0.9232 | 27.0 | 54 | 0.8043 | 39.3574 | | 0.5928 | 28.0 | 56 | 0.8029 | 40.1606 | | 0.5928 | 29.0 | 58 | 0.7987 | 38.3133 | | 0.4714 | 30.0 | 60 | 0.8038 | 37.0281 | | 0.4714 | 31.0 | 62 | 0.8098 | 36.3052 | | 0.4714 | 32.0 | 64 | 0.8083 | 36.7871 | | 0.4555 | 33.0 | 66 | 0.8136 | 38.7149 | | 0.4555 | 34.0 | 68 | 0.8217 | 39.4378 | | 0.4328 | 35.0 | 70 | 0.8310 | 38.6345 | | 0.4328 | 36.0 | 72 | 0.8371 | 37.5904 | | 0.4328 | 37.0 | 74 | 0.8482...

Note14 de set.huggingface.co/tivanai2020/whisper-large-v3-turbo-persian-audiodata2

Source context: 10 downloads · 0 likes · Library peft · Repo tivanai2020/whisper-large-v3-turbo-persian-audiodata2