Xls R Uyghur Cv8

🚀 XLS-R-300M Uyghur CV8

This model is a fine - tuned version of facebook/wav2vec2 - xls - r - 300m on the Uyghur dataset from MOZILLA - FOUNDATION/COMMON_VOICE_8_0. It offers solutions for automatic speech recognition tasks, achieving good results on the evaluation set.

✨ Features

• Fine - tuned Model: Based on the pre - trained facebook/wav2vec2 - xls - r - 300m, fine - tuned on the Uyghur dataset.
• Specific Vocabulary: The model vocabulary consists of the alphabetic characters of the Perso - Arabic script for the Uyghur language, with punctuation removed.
• Low - Fidelity Use Cases: Suitable for draft video captions and indexing of recorded broadcasts.

📚 Documentation

Model description

For a description of the model architecture, see facebook/wav2vec2 - xls - r - 300m. The model vocabulary consists of the alphabetic characters of the Perso - Arabic script for the Uyghur language, with punctuation removed.

Intended uses & limitations

This model is expected to be of some utility for low - fidelity use cases such as:

• Draft video captions
• Indexing of recorded broadcasts

The model is not reliable enough to use as a substitute for live captions for accessibility purposes, and it should not be used in a manner that would infringe the privacy of any of the contributors to the Common Voice dataset nor any other speakers.

Training and evaluation data

The combination of train and dev of common voice official splits were used as training data. The official test split was used as validation data as well as for final evaluation.

Training procedure

The featurization layers of the XLS - R model are frozen while tuning a final CTC/LM layer on the Uyghur CV8 example sentences. A ramped learning rate is used with an initial warmup phase of 2000 steps, a max of 0.0001, and cooling back towards 0 for the remainder of the 9400 steps (100 epochs).

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2000
• num_epochs: 100.0
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.17.0.dev0
• Pytorch 1.10.2+cu102
• Datasets 1.18.3
• Tokenizers 0.11.0

🔧 Technical Details

The model achieves the following results on the evaluation set:

• Loss: 0.2026
• Wer: 0.3248

📄 License

This model is licensed under the Apache - 2.0 license.