susmitabhatt / whisper_nmc_no

huggingface.co
Total runs: 8
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: March 07 2025
automatic-speech-recognition

Introduction of whisper_nmc_no

Model Details of whisper_nmc_no

whisper_nmc_no

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: 0.1467
  • Wer: 9.5335
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 33 0.2012 10.7505
No log 2.0 66 0.2464 67.9513
No log 3.0 99 0.3484 110.9533
1.1664 4.0 132 0.2614 19.6755
1.1664 5.0 165 0.3067 30.4260
1.1664 6.0 198 0.2838 117.0385
0.3564 7.0 231 0.1989 20.8925
0.3564 8.0 264 0.3092 207.0994
0.3564 9.0 297 0.1913 19.0669
0.1486 10.0 330 0.2169 17.4442
0.1486 11.0 363 0.2589 32.8600
0.1486 12.0 396 0.1609 16.0243
0.0731 13.0 429 0.2178 25.3550
0.0731 14.0 462 0.1695 21.7039
0.0731 15.0 495 0.1205 11.1562
0.0238 16.0 528 0.1606 15.4158
0.0238 17.0 561 0.1493 9.9391
0.0238 18.0 594 0.1469 9.9391
0.0046 19.0 627 0.1466 9.7363
0.0046 20.0 660 0.1467 9.5335
Framework versions
  • Transformers 4.50.0.dev0
  • Pytorch 2.5.1+cu121
  • Datasets 3.3.1
  • Tokenizers 0.21.0

Runs of susmitabhatt whisper_nmc_no on huggingface.co

8
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About whisper_nmc_no huggingface.co Model

More whisper_nmc_no license Visit here:

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

whisper_nmc_no huggingface.co

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

susmitabhatt whisper_nmc_no online free

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

susmitabhatt whisper_nmc_no online free url in huggingface.co:

https://huggingface.co/susmitabhatt/whisper_nmc_no

whisper_nmc_no install

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

whisper_nmc_no install url in huggingface.co:

https://huggingface.co/susmitabhatt/whisper_nmc_no

Url of whisper_nmc_no

Provider of whisper_nmc_no huggingface.co

susmitabhatt
ORGANIZATIONS

Other API from susmitabhatt