susmitabhatt / whisper_aii_no_mi

huggingface.co
Total runs: 9
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: March 11 2025
automatic-speech-recognition

Introduction of whisper_aii_no_mi

Model Details of whisper_aii_no_mi

whisper_aii_no_mi

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

  • Loss: 0.0704
  • Wer: 16.6220
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: 0.0004
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • 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: 132
  • num_epochs: 20
  • mixed_precision_training: Native AMP
Training results
Training Loss Epoch Step Validation Loss Wer
No log 1.0 88 0.1184 16.6220
0.8727 2.0 176 0.3031 94.9062
0.2791 3.0 264 0.2692 96.6041
0.278 4.0 352 0.2469 91.5103
0.2434 5.0 440 0.2009 79.0885
0.1973 6.0 528 0.1632 73.1903
0.1536 7.0 616 0.1280 385.1653
0.1367 8.0 704 0.1793 64.6113
0.1367 9.0 792 0.1100 53.2618
0.0789 10.0 880 0.0525 33.1546
0.0391 11.0 968 0.0868 25.2011
0.0384 12.0 1056 0.1299 42.3592
0.0172 13.0 1144 0.0782 21.7158
0.0099 14.0 1232 0.0687 19.8391
0.0077 15.0 1320 0.1135 25.4692
0.0032 16.0 1408 0.0832 28.5970
0.0032 17.0 1496 0.0866 18.5880
0.0009 18.0 1584 0.0710 17.7837
0.0001 19.0 1672 0.0701 16.9794
0.0 20.0 1760 0.0704 16.6220
Framework versions
  • Transformers 4.50.0.dev0
  • Pytorch 2.5.1+cu121
  • Datasets 3.3.1
  • Tokenizers 0.21.0

Runs of susmitabhatt whisper_aii_no_mi on huggingface.co

9
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About whisper_aii_no_mi huggingface.co Model

More whisper_aii_no_mi license Visit here:

https://choosealicense.com/licenses/apache-2.0

whisper_aii_no_mi huggingface.co

whisper_aii_no_mi huggingface.co is an AI model on huggingface.co that provides whisper_aii_no_mi's model effect (), which can be used instantly with this susmitabhatt whisper_aii_no_mi model. huggingface.co supports a free trial of the whisper_aii_no_mi model, and also provides paid use of the whisper_aii_no_mi. Support call whisper_aii_no_mi model through api, including Node.js, Python, http.

susmitabhatt whisper_aii_no_mi online free

whisper_aii_no_mi huggingface.co is an online trial and call api platform, which integrates whisper_aii_no_mi's modeling effects, including api services, and provides a free online trial of whisper_aii_no_mi, you can try whisper_aii_no_mi online for free by clicking the link below.

susmitabhatt whisper_aii_no_mi online free url in huggingface.co:

https://huggingface.co/susmitabhatt/whisper_aii_no_mi

whisper_aii_no_mi install

whisper_aii_no_mi is an open source model from GitHub that offers a free installation service, and any user can find whisper_aii_no_mi on GitHub to install. At the same time, huggingface.co provides the effect of whisper_aii_no_mi install, users can directly use whisper_aii_no_mi installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

whisper_aii_no_mi install url in huggingface.co:

https://huggingface.co/susmitabhatt/whisper_aii_no_mi

Url of whisper_aii_no_mi

whisper_aii_no_mi huggingface.co Url

Provider of whisper_aii_no_mi huggingface.co

susmitabhatt
ORGANIZATIONS

Other API from susmitabhatt