pere commited on
Commit
79c2718
1 Parent(s): 8a7a8c7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -5
README.md CHANGED
@@ -156,16 +156,22 @@ Carbon emissions estimated using the [Machine Learning Impact calculator](https:
156
 
157
  The model is trained using Jax/Flax. The final model is converted to Pytorch, Tensorflow, whisper.cpp and ONXX. Please tell us if you would like future models to be converted to other format.
158
 
159
- ## Citation & Authors
160
- This model was developed within the scope of the _NoSTram_ project, led by _Per Egil Kummervold_. The Jax code and training scripts were crafted by _Javier de la Rosa_, _Freddy Wetjen_, _Rolv-Arild Braaten_, and _Per Egil Kummervold_. Dataset curation was carried out by _Freddy Wetjen_, _Rolv-Arild Braaten_, and _Per Egil Kummervold_. Documentation was composed by _Javier de la Rosa_ and _Per Egil Kummervold_. The AiLab is under the direction of _Svein Arne Brygfjeld_. Each author contributed to the development and deliberations on the optimal way to train a Norwegian ASR model using Whisper. The work on this model was conducted as part of our professional roles at the National Library of Norway.
 
 
 
 
161
 
162
- _A paper is coming soon!_
163
 
164
- If you intend to incorporate this model into your research, we kindly request that you reach out to us. We can provide you with the most current status of our upcoming paper, which you can cite to acknowledge and provide context for the work done on this model.
165
  ## Acknowledgements
166
 
167
  Thanks to [Google TPU Research Cloud](https://sites.research.google/trc/about/) for supporting this project with extensive training resources. Thanks to Google Cloud for supporting us with credits for translating large parts of the corpus. A special thanks to [Sanchit Ghandi](https://huggingface.co/sanchit-gandhi) for providing thorough technical advice in debugging and with the work of getting this to train on Google TPUs. A special thanks to Per Erik Solberg at Språkbanken for the collaboration with regard to the Stortinget corpus.
168
 
169
  ## Contact
170
  We are releasing this ASR Whisper model as a public beta to garner constructive feedback on its performance. Please do not hesitate to contact us with any experiences, insights, or suggestions that you may have. Your input is invaluable in helping us to improve the model and ensure that it effectively serves the needs of users. Whether you have technical concerns, usability suggestions, or ideas for future enhancements, we welcome your input. Thank you for participating in this critical stage of our model's development.
171
- <a rel="noopener nofollow" href="mailto:ailab@nb.no">ailab@nb.no</a>
 
 
 
 
 
156
 
157
  The model is trained using Jax/Flax. The final model is converted to Pytorch, Tensorflow, whisper.cpp and ONXX. Please tell us if you would like future models to be converted to other format.
158
 
159
+ ## Citation & Contributors
160
+ The development of this model was part of the contributors' professional roles at the National Library of Norway, under the _NoSTram_ project led by _Per Egil Kummervold (PEK)_. The Jax code, dataset loaders, and training scripts were collectively designed by _Javier de la Rosa (JdlR)_, _Freddy Wetjen (FW)_, _Rolv-Arild Braaten (RAB)_, and _PEK_. Primary dataset curation was handled by _FW_, _RAB_, and _PEK_, while _JdlR_ and _PEK_ crafted the documentation. The project was completed under the umbrella of AiLab, directed by _Svein Arne Brygfjeld_.
161
+
162
+ All contributors played a part in shaping the optimal training strategy for the Norwegian ASR model, Whisper.
163
+
164
+ _A paper detailing our process and findings is underway!_
165
 
 
166
 
 
167
  ## Acknowledgements
168
 
169
  Thanks to [Google TPU Research Cloud](https://sites.research.google/trc/about/) for supporting this project with extensive training resources. Thanks to Google Cloud for supporting us with credits for translating large parts of the corpus. A special thanks to [Sanchit Ghandi](https://huggingface.co/sanchit-gandhi) for providing thorough technical advice in debugging and with the work of getting this to train on Google TPUs. A special thanks to Per Erik Solberg at Språkbanken for the collaboration with regard to the Stortinget corpus.
170
 
171
  ## Contact
172
  We are releasing this ASR Whisper model as a public beta to garner constructive feedback on its performance. Please do not hesitate to contact us with any experiences, insights, or suggestions that you may have. Your input is invaluable in helping us to improve the model and ensure that it effectively serves the needs of users. Whether you have technical concerns, usability suggestions, or ideas for future enhancements, we welcome your input. Thank you for participating in this critical stage of our model's development.
173
+
174
+ If you intend to incorporate this model into your research, we kindly request that you reach out to us. We can provide you with the most current status of our upcoming paper, which you can cite to acknowledge and provide context for the work done on this model.
175
+
176
+
177
+ Please use this email as the main contact point, it is read by the entire team: <a rel="noopener nofollow" href="mailto:ailab@nb.no">ailab@nb.no</a>