Add acknowlegments and contact info to README

README.md

@@ -60,6 +60,8 @@ This model is a version of [facebook/wav2vec2-xls-r-2b-22-to-16](https://hugging
 >
 > You can compare the [predictions](https://huggingface.co/FremyCompany/xls-r-2b-nl-v2_lm-5gram-os2_hunspell/blob/main/log_speech-recognition-community-v2_dev_data_nl_validation_predictions.txt) with the [targets](https://huggingface.co/FremyCompany/xls-r-2b-nl-v2_lm-5gram-os2_hunspell/blob/main/log_speech-recognition-community-v2_dev_data_nl_validation_targets.txt) on the validation dev set yourself, for example using [this diffing tool](https://countwordsfree.com/comparetexts).
 
+> **WE DO SPEECH RECOGNITION**: Hello reader! If you are considering using this (or another) model in production, but would benefit from a model fine-tuned specifically for your use case (using text and/or labelled speech), feel free to [contact our team](https://www.ugent.be/ea/idlab/en/research/semantic-intelligence/speech-and-audio-processing.htm). This model was developped during the [Robust Speech Recognition challenge](https://discuss.huggingface.co/t/open-to-the-community-robust-speech-recognition-challenge/13614) event by [François REMY](https://www.linkedin.com/in/fremycompany/) [(twitter)](https://twitter.com/FremyCompany) and [Geoffroy VANDERREYDT](https://be.linkedin.com/in/geoffroy-vanderreydt-a4421460). We would like to thank [OVH](https://www.ovhcloud.com/en/public-cloud/ai-training/) for providing us with a V100S GPU.
+
 ## Model description
 
 The model takes 16kHz sound input, and uses a Wav2Vec2ForCTC decoder with 48 letters to output the letter-transcription probabilities per frame.