Wav2vec2 Xls R 300m Cv8 Turkish

🚀 wav2vec2-xls-r-300m-cv8-turkish

This is an Automatic Speech Recognition (ASR) model fine - tuned for the Turkish language.

🚀 Quick Start

Before running evaluation, please install the unicode_tr package, which is used for Turkish text processing.

Evaluate on mozilla-foundation/common_voice_8_0 with split test

python eval.py --model_id mpoyraz/wav2vec2-xls-r-300m-cv8-turkish --dataset mozilla-foundation/common_voice_8_0 --config tr --split test

Evaluate on speech-recognition-community-v2/dev_data

python eval.py --model_id mpoyraz/wav2vec2-xls-r-300m-cv8-turkish --dataset speech-recognition-community-v2/dev_data --config tr --split validation --chunk_length_s 5.0 --stride_length_s 1.0

✨ Features

• This ASR model is a fine - tuned version of facebook/wav2vec2-xls-r-300m on the Turkish language.
• An N - gram language model is trained on Turkish Wikipedia articles using KenLM.

📦 Installation

No specific installation steps are provided in the original document.

📚 Documentation

Model Description

This ASR model is a fine - tuned version of facebook/wav2vec2-xls-r-300m on the Turkish language.

Training and Evaluation Data

The following datasets were used for finetuning:

• Common Voice 8.0 TR. All validated split except the test split was used for training.

Training Procedure

To support the above datasets, custom pre - processing and loading steps were performed, and the wav2vec2-turkish repo was used for that purpose.

Training Hyperparameters

The following hyperparameters were used for finetuning:

• learning_rate: 2.5e - 4
• num_train_epochs: 20
• warmup_steps: 500
• freeze_feature_extractor
• mask_time_prob: 0.1
• mask_feature_prob: 0.1
• feat_proj_dropout: 0.05
• attention_dropout: 0.05
• final_dropout: 0.1
• activation_dropout: 0.05
• per_device_train_batch_size: 8
• per_device_eval_batch_size: 8
• gradient_accumulation_steps: 8

Framework Versions

• Transformers: 4.17.0.dev0
• Pytorch: 1.10.1
• Datasets: 1.17.0
• Tokenizers: 0.10.3

Language Model

An N - gram language model is trained on Turkish Wikipedia articles using KenLM, and the ngram-lm-wiki repo was used to generate an arpa LM and convert it into binary format.

Evaluation Results

🔧 Technical Details

The model mpoyraz/wav2vec2-xls-r-300m-cv8-turkish is a fine - tuned version of facebook/wav2vec2-xls-r-300m for the Turkish language. Custom pre - processing and loading steps are performed to support the mozilla-foundation/common_voice_8_0 dataset. Hyperparameters are carefully selected for finetuning, and an N - gram language model is trained on Turkish Wikipedia articles using KenLM.

📄 License

This model is licensed under the Apache 2.0 license.

📊 Model Index

• Name: mpoyraz/wav2vec2-xls-r-300m-cv8-turkish Results:
  • Task: Name: Automatic Speech Recognition Type: automatic - speech - recognition Dataset: Name: Common Voice 8 Type: mozilla - foundation/common_voice_8_0 Args: tr Metrics:
    • Name: Test WER Type: wer Value: 10.61
    • Name: Test CER Type: cer Value: 2.67
  • Task: Name: Automatic Speech Recognition Type: automatic - speech - recognition Dataset: Name: Robust Speech Event - Dev Data Type: speech - recognition - community - v2/dev_data Args: tr Metrics:
    • Name: Test WER Type: wer Value: 36.46
    • Name: Test CER Type: cer Value: 12.38
  • Task: Name: Automatic Speech Recognition Type: automatic - speech - recognition Dataset: Name: Robust Speech Event - Test Data Type: speech - recognition - community - v2/eval_data Args: tr Metrics:
    • Name: Test WER Type: wer Value: 40.91