arijitx commited on
Commit
c990515
·
verified ·
1 Parent(s): 9617cfd

Fix training data stats: remove indicvoices_r

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -1,3 +1,4 @@
 
1
  ---
2
  license: mit
3
  language:
@@ -19,11 +20,10 @@ A fine-tuned version of [ResembleAI/chatterbox](https://huggingface.co/ResembleA
19
  ## Model Details
20
 
21
  - **Base model**: ResembleAI/chatterbox (0.5B Llama-based TTS)
22
- - **Fine-tuned on**: Bengali speech corpus (~103 hours)
23
- - ai4bharat/Shrutilipi (Bengali split) — 17,882 samples
24
- - ai4bharat/Rasa (Bengali split) — 28,088 samples
25
- - SPRINGLab/IndicTTS_Bengali — 12,852 samples
26
- - ai4bharat/indicvoices_r (Bengali split) — 1,500 samples
27
  - **Training steps**: 20,000
28
  - **Epochs**: ~10.6
29
  - **Architecture**: T3 (Text-to-Token Transformer) + HiFT-GAN vocoder
 
1
+ \
2
  ---
3
  license: mit
4
  language:
 
20
  ## Model Details
21
 
22
  - **Base model**: ResembleAI/chatterbox (0.5B Llama-based TTS)
23
+ - **Fine-tuned on**: Bengali speech corpus (~99 hours, 58,820 samples)
24
+ - ai4bharat/Shrutilipi (Bengali split) — 17,882 samples, ~28h
25
+ - ai4bharat/Rasa (Bengali split) — 28,088 samples, ~51h
26
+ - SPRINGLab/IndicTTS_Bengali — 12,852 samples, ~20h
 
27
  - **Training steps**: 20,000
28
  - **Epochs**: ~10.6
29
  - **Architecture**: T3 (Text-to-Token Transformer) + HiFT-GAN vocoder