CoolFace
Modelpublic

ishmamzarif/bangla_asr_augmented_bangla-whisper-epoch-11

sourceHugging Facemitupdated 10mo agoView on Hugging Face
0likes10downloads
Model Card

Model Details

Bangla dialect ASR (Automatic Speech Recognition) Model

Model Sources:

  • —Repository: https://huggingface.co/bangla-speech-processing/BanglaASR
Training Hyperparameters
  • —Batch Size: 4
  • —Learning rate: 3e-5
  • —Warmup Steps: 750
  • —Epochs: 12
  • —Gradient Accumulation Steps: 4
  • —LR Scheduler: linear
  • —Weight decay: 0.005

Evaluation

EpochTraining LossValidation LossWERNormalized Levenshtein Similarity
01.0794000.96340439.89735376.774691
20.8164000.84443323.71691085.590027
40.7774000.81421217.50405289.011984
60.7560000.80024516.07239389.814135
80.7467000.79416712.88492791.766032
100.7428000.79184611.69638092.622563
110.7425000.79274811.93949292.488058

Language and Environment

  • —Python version: 3.12.12
  • —PyTorch version: 2.8.0+cu126
  • —Transformers version: 4.44.2
  • —NumPy version: 1.26.4

CUDA Info

  • —GPU: Tesla T4
  • —GPU Memory: 15.83 GB