bharat-raghunathan
/

Tamil-Wav2Vec-xls-r-300m-Tamil-colab

Automatic Speech Recognition

Generated from Trainer

robust-speech-event

Model card Files Files and versions

Metrics Training metrics Community

Tamil-Wav2Vec-xls-r-300m-Tamil-colab

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset.

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: 30
mixed_precision_training: Native AMP

Framework versions

Transformers 4.11.3
Pytorch 1.10.0+cu111
Datasets 1.18.3
Tokenizers 0.10.3

Downloads last month: 13

Safetensors

Model size

0.3B params

Tensor type

F32

·

Dataset used to train bharat-raghunathan/Tamil-Wav2Vec-xls-r-300m-Tamil-colab

Space using bharat-raghunathan/Tamil-Wav2Vec-xls-r-300m-Tamil-colab 1