Hugging Face's logo

UmarRamzan
/
w2v2-bert-ngram-urdu

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Urdu
wav2vec2-bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
w2v2-bert-ngram-urdu / README.md
UmarRamzan's picture
UmarRamzan
Upload folder using huggingface_hub
f7997cf verified
preview code
|
raw
history blame
1.73 kB
metadata
license: mit
base_model: UmarRamzan/w2v2-bert-urdu
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: w2v2-bert-urdu
    results: []

w2v2-bert-urdu

This model is a fine-tuned version of UmarRamzan/w2v2-bert-urdu on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3681
  • Wer: 0.2929

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: 5e-06
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.4362 0.1695 50 0.4144 0.3213
0.3776 0.3390 100 0.4029 0.3137
0.3918 0.5085 150 0.4095 0.3060
0.3968 0.6780 200 0.3961 0.3060
0.3685 0.8475 250 0.3681 0.2929

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1