Akashpb13/xlsr_kurmanji_kurdish

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - hu dataset. It achieves the following results on the evaluation set (which is 10 percent of train data set merged with invalidated data, reported, other, and dev datasets):

• Loss: 0.292389
• Wer: 0.388585

Model description

"facebook/wav2vec2-xls-r-300m" was finetuned.

Intended uses & limitations

More information needed

Training and evaluation data

Training data - Common voice Kurmanji Kurdish train.tsv, dev.tsv, invalidated.tsv, reported.tsv, and other.tsv Only those points were considered where upvotes were greater than downvotes and duplicates were removed after concatenation of all the datasets given in common voice 7.0

Training procedure

For creating the training dataset, all possible datasets were appended and 90-10 split was used.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.000096
• train_batch_size: 16
• eval_batch_size: 16
• seed: 13
• gradient_accumulation_steps: 16
• lr_scheduler_type: cosine_with_restarts
• lr_scheduler_warmup_steps: 200
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.16.0.dev0
• Pytorch 1.10.0+cu102
• Datasets 1.18.1
• Tokenizers 0.10.3

Evaluation Commands

1. To evaluate on mozilla-foundation/common_voice_8_0 with split test

python eval.py --model_id Akashpb13/xlsr_kurmanji_kurdish --dataset mozilla-foundation/common_voice_8_0 --config kmr --split test