# Baseline model vs finetuned model for multilingual speech recognition

**URL:** <https://discuss.huggingface.co/t/baseline-model-vs-finetuned-model-for-multilingual-speech-recognition/23356>\
**Category:** Beginners\
**Created:** [September 19, 2022, 5:41pm UTC](https://discuss.huggingface.co/t/baseline-model-vs-finetuned-model-for-multilingual-speech-recognition/23356 "2022-09-19T17:41:40Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![throwara](https://avatars.discourse-cdn.com/v4/letter/t/ee7513/32.png) [@throwara](https://discuss.huggingface.co/u/throwara)\
**Post date:** [September 19, 2022, 5:41pm UTC](https://discuss.huggingface.co/t/baseline-model-vs-finetuned-model-for-multilingual-speech-recognition/23356/1 "2022-09-19T17:41:41Z")

</div>

Hi, I would like to recognize multilingual speech to translate them to English for further processing and I have a few questions related to it.

1. What is the difference between using a baseline model vs a fine-tuned model at a specific language?  
[facebook/wav2vec2-large-xlsr-53 · Hugging Face](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) vs [jonatasgrosman/wav2vec2-large-xlsr-53-english · Hugging Face](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english).  
Which one do I use out of those and what is the difference between them? Aren’t they the same models?

2. Can I use XLSR-53 to recognize multilingual speech by itself? Or should I fine-tune the model in each of the 53 languages and store 53 versions of the model (one for each language) and use it like that? Do I have to append language related tokens to the start of the model inputs so that it will recognize speech from that language?