Hebrew
dual_ar
sleeping4cat commited on
Commit
5b1cc79
·
verified ·
1 Parent(s): 57883a8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -2,8 +2,13 @@
2
  license: mit
3
  datasets:
4
  - upai-inc/saspeech
 
5
  language:
6
  - he
7
  base_model:
8
  - fishaudio/fish-speech-1.5
9
- ---
 
 
 
 
 
2
  license: mit
3
  datasets:
4
  - upai-inc/saspeech
5
+ - sleeping-ai/Fish-Hebrew
6
  language:
7
  - he
8
  base_model:
9
  - fishaudio/fish-speech-1.5
10
+ ---
11
+
12
+ Hebrew is fundamentally a hard language to work in the field of Natural language processing and it is also one of the underrepresented language in the field of Speech-Speech and Text-to-Speech models. Mainly boils down to limited availability of data. To explore Speech-Speech **(Voice Cloning)**, I used [Dataset](https://www.isca-archive.org/interspeech_2023/sharoni23_interspeech.pdf) to fine-tune Fish-speech 1.5 on roughly 2.5 hours of Hebrew audio on their Gold-standard subset.
13
+
14
+ I have also fixed a few bugs on Fish's fine-tuning code and created a [pull-request](https://github.com/fishaudio/fish-speech/pull/973)