Edit model card

wav2vec2-large-xls-r-300m-assamese_speech_to_IPA_with_wer_cer_f1

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8170
  • Exact Match: 0.0325
  • F1: 0.0325
  • Wer: 0.9675
  • Cer: 0.1450

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: 0.0003
  • 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: 500
  • num_epochs: 40
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Exact Match F1 Wer Cer
4.6801 9.8765 400 0.8184 0.0032 0.0032 0.9968 0.2199
0.2678 19.7531 800 0.7753 0.0227 0.0227 0.9773 0.1628
0.1009 29.6296 1200 0.8270 0.0292 0.0292 0.9708 0.1504
0.0619 39.5062 1600 0.8170 0.0325 0.0325 0.9675 0.1450

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
315M params
Tensor type
F32
·
Inference API
or
This model can be loaded on Inference API (serverless).

Finetuned from

Evaluation results