Yurii Paniv commited on
Commit
1f211a9
โ€ข
1 Parent(s): 1fbddb5

Reorganize repo

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  title: "Ukrainian Speech-to-Text"
3
- emoji: ๐Ÿธ
4
  colorFrom: blue
5
  colorTo: yellow
6
  sdk: gradio
@@ -9,20 +9,28 @@ pinned: false
9
  ---
10
 
11
  # ๐Ÿ‡บ๐Ÿ‡ฆ๐ŸŽค Voice recognition for Ukrainian language
12
- This is a repository with aim to apply [Coqui STT](https://github.com/coqui-ai/STT "STT")(formerly [DeepSpeech](https://github.com/mozilla/DeepSpeech)) speech recognition model on Ukrainian language.
 
13
  You can see online demo here: https://huggingface.co/spaces/robinhad/ukrainian-stt.
14
  Source code is in this repository together with auto-deploy pipeline scripts.
15
 
16
- Model trained using non-free data is licensed under [Creative Commons Attribution-NonCommercial 4.0 International License](./LICENSE), otherwise it's MIT licence (where models are marked).
 
 
 
 
 
 
17
 
18
  Checkout latest releases here: https://github.com/robinhad/voice-recognition-ua/releases/.
19
 
20
  If you'd like to check out different models for Ukrainian language, please visit https://github.com/egorsmkv/speech-recognition-uk.
21
 
22
- # ๐Ÿค– Data import scripts
23
- Guides for importing data are available in [/scripts](/scripts) folder.
24
 
25
  # ๐Ÿค Attribution
 
26
  [@egorsmkv](https://github.com/egorsmkv) - organized [Ukrainian Speech recognition community](https://github.com/egorsmkv/speech-recognition-uk).
27
- [@tarasfrompir](https://github.com/tarasfrompir) - created amazing Ukrainian Speech-to-Text dataset.
28
  [@AlexeyBoiler](https://github.com/AlexeyBoiler) - hosted Ukrainian Speech-to-Text dataset.
 
1
  ---
2
  title: "Ukrainian Speech-to-Text"
3
+ emoji: ๐ŸŒ
4
  colorFrom: blue
5
  colorTo: yellow
6
  sdk: gradio
 
9
  ---
10
 
11
  # ๐Ÿ‡บ๐Ÿ‡ฆ๐ŸŽค Voice recognition for Ukrainian language
12
+ This is a repository with aim to apply various speech recognition models on Ukrainian language.
13
+
14
  You can see online demo here: https://huggingface.co/spaces/robinhad/ukrainian-stt.
15
  Source code is in this repository together with auto-deploy pipeline scripts.
16
 
17
+
18
+ # ๐Ÿงฎ Models
19
+ Model name | CER | WER | License | Note
20
+ :-------------------------|:-------------------------|:-------------------------|:-------------------------|:-------------------------
21
+ [DeepSpeech with Wiki LM](https://github.com/robinhad/voice-recognition-ua/releases/tag/v0.4) | 12% | 30,65% | CC-BY-NC 4.0 | Common Voice 6 dataset
22
+ [DeepSpeech](https://github.com/robinhad/voice-recognition-ua/releases/tag/v0.4) | 16% | 57% | CC-BY-NC 4.0 | Common Voice 6 dataset
23
+
24
 
25
  Checkout latest releases here: https://github.com/robinhad/voice-recognition-ua/releases/.
26
 
27
  If you'd like to check out different models for Ukrainian language, please visit https://github.com/egorsmkv/speech-recognition-uk.
28
 
29
+ # ๐Ÿค– Training scripts
30
+ Guides for training are available in corresponding folders for each model.
31
 
32
  # ๐Ÿค Attribution
33
+ [@robinhad](https://github.com/robinhad) - model training.
34
  [@egorsmkv](https://github.com/egorsmkv) - organized [Ukrainian Speech recognition community](https://github.com/egorsmkv/speech-recognition-uk).
35
+ [@tarasfrompir](https://github.com/tarasfrompir) - created synthetic 1200h Ukrainian Speech-to-Text dataset.
36
  [@AlexeyBoiler](https://github.com/AlexeyBoiler) - hosted Ukrainian Speech-to-Text dataset.
{scripts โ†’ deepspeech}/README.md RENAMED
File without changes
{scripts โ†’ deepspeech}/extract_text_corpus.py RENAMED
File without changes
{scripts โ†’ deepspeech}/import_ukrainian.py RENAMED
File without changes
{scripts โ†’ deepspeech}/wiki_import.py RENAMED
File without changes