wav2vec2-xls-r-300m-hindi-lm This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the 'Openslr Multilingual and code-switching ASR challenge' dataset and 'mozilla-foundation/common_voice_7_0' dataset. It achieves the following results on the evaluation set:

With language model: WER: 0.3421149821494522 CER: 0.12281403517543969

With out language model: WER: 0.4642989043456851 CER: 0.15765197064963313