GetmanY1 commited on
Commit
2632008
·
verified ·
1 Parent(s): e810386

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +26 -2
README.md CHANGED
@@ -16,7 +16,7 @@ The large model pre-trained on 16kHz sampled speech audio. When using the model
16
 
17
  The Finnish Wav2Vec2 Large has the same architecture and uses the same training objective as the English and multilingual one described in [Paper](https://arxiv.org/abs/2006.11477). It is pre-trained on 2600 hours of unlabeled colloquial Finnish speech from [Lahjoita puhetta (Donate Speech)](https://link.springer.com/article/10.1007/s10579-022-09606-3).
18
 
19
- You can read more about the pre-trained model from [this paper](TODO).
20
 
21
  ## Intended uses & limitations
22
 
@@ -30,4 +30,28 @@ See [this notebook](https://colab.research.google.com/github/patrickvonplaten/no
30
 
31
  This model was pre-trained with audio samples whose maximum length was 60 seconds so this model most likely works the best for quite short audios of similar length. However, you can try this model with a lot longer audios too and see how it works. If you encounter out of memory errors with very long audio files you can use the audio chunking method introduced in [this blog post](https://huggingface.co/blog/asr-chunking).
32
 
33
- A vast majority of the data used for pre-training was from the [Lahjoita puhetta (Donate Speech) corpus](https://link.springer.com/article/10.1007/s10579-022-09606-3) so this model might have biases towards colloquial Finnish.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
 
17
  The Finnish Wav2Vec2 Large has the same architecture and uses the same training objective as the English and multilingual one described in [Paper](https://arxiv.org/abs/2006.11477). It is pre-trained on 2600 hours of unlabeled colloquial Finnish speech from [Lahjoita puhetta (Donate Speech)](https://link.springer.com/article/10.1007/s10579-022-09606-3).
18
 
19
+ You can read more about the pre-trained model from [this paper](TODO). The training scripts are available on [GitHub](https://github.com/aalto-speech/colloquial-Finnish-wav2vec2)
20
 
21
  ## Intended uses & limitations
22
 
 
30
 
31
  This model was pre-trained with audio samples whose maximum length was 60 seconds so this model most likely works the best for quite short audios of similar length. However, you can try this model with a lot longer audios too and see how it works. If you encounter out of memory errors with very long audio files you can use the audio chunking method introduced in [this blog post](https://huggingface.co/blog/asr-chunking).
32
 
33
+ A vast majority of the data used for pre-training was from the [Lahjoita puhetta (Donate Speech) corpus](https://link.springer.com/article/10.1007/s10579-022-09606-3) so this model might have biases towards colloquial Finnish.
34
+
35
+ ## Citation
36
+
37
+ If you use our models or scripts, please cite our article as:
38
+
39
+ ```bibtex
40
+ @inproceedings{getman24a_interspeech,
41
+ author={Yaroslav Getman and Tamas Grosz and Mikko Kurimo},
42
+ title={{What happens in continued pre-training? Analysis of self-supervised speech
43
+ models with continued pre-training for colloquial Finnish ASR}},
44
+ year=2024,
45
+ booktitle={Proc. INTERSPEECH 2024},
46
+ pages={XX--XX},
47
+ doi={XXXX},
48
+ issn={XXXX-XXXX}
49
+ }
50
+ ```
51
+
52
+ ## Team Members
53
+
54
+ - Yaroslav Getman, [Hugging Face profile](https://huggingface.co/GetmanY1), [LinkedIn profile](https://www.linkedin.com/in/yaroslav-getman/)
55
+ - Tamas Grosz, [Hugging Face profile](https://huggingface.co/Grosy), [LinkedIn profile](https://www.linkedin.com/in/tam%C3%A1s-gr%C3%B3sz-950a049a/)
56
+
57
+ Feel free to contact us for more details 🤗