We study the effect of applying a language model (LM) on the output of Automatic Speech Recognition (ASR) systems for Indic languages. We fine-tune wav2vec $2.0$ models for $18$ Indic languages and adjust the results with language models trained on text derived from a variety of sources. Our findings demonstrate that the average Character Error Rate (CER) decreases by over $28$ \% and the average Word Error Rate (WER) decreases by about $36$ \% after decoding with LM. We show that a large LM may not provide a substantial improvement as compared to a diverse one. We also demonstrate that high quality transcriptions can be obtained on domain-specific data without retraining the ASR model and show results on biomedical domain.

本文探究了应用语言模型（LM）到印欧语系语言的自动语音识别（ASR）系统输出结果的影响。我们使用来自多种来源的文本对 18 种印欧语系语言的 wav2vec 2.0 模型进行微调，并进行结果调整。我们的研究结果显示，经过 LM 解码后，字符错误率（CER）平均降低了 28％以上，单词错误率（WER）平均降低了约 36％。文章还表明，与多样化的 LM 相比，大型 LM 可能不会带来更大的改进。此外，我们还展示了可以在不重新训练 ASR 模型的情况下在生物医学领域的专业数据上获得高质量翻译的结果。

利用语言模型提高印度语言的语音识别