dinhthuan commited on
Commit
f6f4c6a
·
verified ·
1 Parent(s): ffacb6a

Upload FP16 checkpoint 920k: README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -20,7 +20,7 @@ Vietnamese zero-shot TTS / voice cloning fine-tuned from [ZipVoice](https://gith
20
  - GitHub: https://github.com/iamdinhthuan/ViZipvoice
21
  - Model repo: https://huggingface.co/contextboxai/ViZipvoice
22
  - Space: https://huggingface.co/spaces/dinhthuan/ViZipvoice
23
- - Latest checkpoint: `checkpoint-700000.pt`, FP16 inference state dict
24
  - Training data: about `7000` total hours, including roughly `6500` hours of Vietnamese and `500` hours of English
25
  - Tokenizer: `SimpleTokenizer`, character-level, `244` tokens
26
  - Sample rate: `24 kHz`
@@ -129,7 +129,8 @@ Useful knobs:
129
 
130
  ## Files
131
 
132
- - `checkpoint-700000.pt`: latest FP16 checkpoint
 
133
  - `config.json`, `model.json`: model config
134
  - `tokens.txt`: Vietnamese character tokenizer
135
  - `audio/`: 30 reference audios plus `.txt` transcripts
 
20
  - GitHub: https://github.com/iamdinhthuan/ViZipvoice
21
  - Model repo: https://huggingface.co/contextboxai/ViZipvoice
22
  - Space: https://huggingface.co/spaces/dinhthuan/ViZipvoice
23
+ - Latest checkpoint: `checkpoint-920000.pt`, FP16 inference state dict
24
  - Training data: about `7000` total hours, including roughly `6500` hours of Vietnamese and `500` hours of English
25
  - Tokenizer: `SimpleTokenizer`, character-level, `244` tokens
26
  - Sample rate: `24 kHz`
 
129
 
130
  ## Files
131
 
132
+ - `checkpoint-920000.pt`: latest FP16 checkpoint
133
+ - `checkpoint-700000.pt`: previous FP16 checkpoint used for the current demo audios
134
  - `config.json`, `model.json`: model config
135
  - `tokens.txt`: Vietnamese character tokenizer
136
  - `audio/`: 30 reference audios plus `.txt` transcripts