SWivid commited on
Commit
f8ee9db
·
verified ·
1 Parent(s): 880b7c9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -3
README.md CHANGED
@@ -1,3 +1,29 @@
1
- ---
2
- license: cc-by-nc-sa-4.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ datasets:
4
+ - sqrk/mixat-tri
5
+ - facebook/omnilingual-asr-corpus
6
+ - ArabicSpeech/MGB-3
7
+ - MightyStudent/Egyptian-ASR-MGB-3
8
+ - google/fleurs
9
+ - ArabicSpeech/MGB-5
10
+ - Nexdata/UAE_Arabic_Spontaneous_Speech_Data
11
+ - AhmedBadawy11/UAE_100K
12
+ - adiren7/darija_speech_to_text
13
+ - KandirResearch/DarijaTTS-clean
14
+ - nadsoft/Jordan-Audio
15
+ language:
16
+ - ar
17
+ base_model:
18
+ - SWivid/F5-TTS
19
+ ---
20
+
21
+ # A suite of specialized and unified dialectal Arabic TTS models
22
+
23
+ Paper: "Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis"
24
+ Github: https://github.com/SWivid/Habibi-TTS
25
+
26
+
27
+ > [!NOTE]
28
+ > The unified, SAU, and UAE models are licensed under CC-BY-NC-SA-4.0, restricted by [SADA](https://www.kaggle.com/datasets/sdaiancai/sada2022) and [Mixat](https://huggingface.co/datasets/sqrk/mixat-tri) datasets.
29
+ > All the rest (ALG, EGY, IRQ, MAR, MSA) are released under Apache 2.0 license.