土耳其语语音转文本的预训练模型性能比较：Whisper-Small 与 Wav2Vec2-XLS-R-300M
Performance Comparison of Pre-trained Models for Speech-to-Text in Turkish: Whisper-Small and Wav2Vec2-XLS-R-300M
AI总结：
本文比较 Whisper-Small 与 Wav2Vec2-XLS-R-300M 在土耳其语语音转文本任务上的性能，使用 Mozilla Common Voice 11.0 微调，并以呼叫中心数据测试，Whisper-Small 的 WER 更低。
摘要：
本研究考察了 Whisper-Small 和 Wav2Vec2-XLS-R-300M 这两个用于语音转文本的预训练多语言模型在土耳其语上的性能。研究使用了以土耳其语制作的开源数据集 Mozilla Common Voice 版本 11.0。Whisper-Small 和 Wav2Vec2-XLS-R-300M 这两个多语言模型使用这一数据量较小的数据集进行了微调。研究比较了两个模型的语音转文本性能。Wav2Vec2-XLS-R-300M 和 Whisper-Small 的 WER 值分别计算为 0.28 和 0.16。此外，还使用未包含在训练和验证数据集中的呼叫中心记录制作的测试数据检验了模型性能。
英文摘要：
In this study, the performances of the Whisper-Small and Wav2Vec2-XLS-R-300M models which are two pre-trained multilingual models for speech to text were examined for the Turkish language. Mozilla Common Voice version 11.0 which is prepared in Turkish language and is an open-source data set, was used in the study. The multilingual models, Whisper- Small and Wav2Vec2-XLS-R-300M were fine-tuned with this data set which contains a small amount of data. The speech to text performance of the two models was compared. WER values are calculated as 0.28 and 0.16 for the Wav2Vec2-XLS- R-300M and the Whisper-Small models respectively. In addition, the performances of the models were examined with the test data prepared with call center records that were not included in the training and validation dataset.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
