Skip to content
ModelListedExternal
Browse files

IndexTTS Postrain

bigvgandiscriminator.pth bigvgangenerator.pth bpe.model (tokenizer) config.yaml (original inference configuration) gpt.pth (backbone transformer) dvae.pth (use for getting training audio tokens) unigram12000.vocab...

Sourcehuggingface.co/sylvia-xiao/IndexTTS_postrain/tree/eaba1e35489e91a1174e6ea0a6bfd4e66f3577ce
KindOtherVersionRevision eaba1e3Cgrade

Model source

Kind
Other
File size
232 MB–2.19 GB
Version
vRevision eaba1e3
Updated
Oct 20, 2026
Downloads
3
Source
Hugging Face

Source description

This is a brief introduction for model ckpts.

original models:

  1. bigvgan_discriminator.pth
  2. bigvgan_generator.pth
  3. bpe.model (tokenizer)
  4. config.yaml (original inference configuration)
  5. gpt.pth (backbone transformer)
  6. dvae.pth (use for getting training audio tokens)
  7. unigram_12000.vocab (tokenizer vocabulary)

fine-tuned models:

  1. Cantonese Model: a. config_yue.yaml b. gpt_tuned_yue.pth c. gpt_yue.pth (useless only for start stage in training)
  2. Janpanese Model: a. config_ja.yaml b. gpt_tuned_ja.pth c. gpt_tuned_ja_v2.pth c. gpt_ja.pth (useless only for start stage in training)
  3. Malaya Model: a. config_malay.yaml b. gpt_malaya_tuned.pth c. gpt_malay.pth (useless only for start stage in training)

Sources

1 source
Hugging FacePrimaryVersion eaba1e35489e91a1174e6ea0a6bfd4e66f3577ce
huggingface.co/sylvia-xiao/IndexTTS_postrain/tree/eaba1e35489e91a1174e6ea0a6bfd4e66f3577ce

Verified Aug 30

Download files

Model artifacts

13 artifacts

bigvgan_discriminator.pth

pth · 1.54 GB · SHA-256 46e1f6277f72…02f0 · Hugging Face

Download file

bigvgan_generator.pth

pth · 511 MB · SHA-256 a2458834d827…33ed · Hugging Face

Download file

dvae copy.pth

pth · 232 MB · SHA-256 69e841bf8cd9…4d5d · Hugging Face

Download file

dvae.pth

pth · 232 MB · SHA-256 69e841bf8cd9…4d5d · Hugging Face

Download file

gpt_hoho.pth

pth · 1.09 GB · SHA-256 2680f7134cc0…63b0 · Hugging Face

Download file

gpt_ja.pth

pth · 1.09 GB · SHA-256 19d710454770…fbf6 · Hugging Face

Download file

gpt_malay.pth

pth · 1.09 GB · SHA-256 df4bf1a9bb1d…8e24 · Hugging Face

Download file

gpt_tuned_ja_v2.pth

pth · 2.18 GB · SHA-256 bba8b2b4c557…38d9 · Hugging Face

Download file

gpt_tuned_ja.pth

pth · 2.18 GB · SHA-256 c604f250dcb7…263e · Hugging Face

Download file

gpt_tuned_malaya.pth

pth · 2.18 GB · SHA-256 f9dcc716885a…9fc2 · Hugging Face

Download file

gpt_tuned_yue.pth

pth · 2.19 GB · SHA-256 03b996d76e79…c6c0 · Hugging Face

Download file

gpt_yue.pth

pth · 1.09 GB · SHA-256 8212e56e1eaa…829d · Hugging Face

Download file

gpt.pth

pth · 1.09 GB · SHA-256 44460b820a8a…1240 · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeAug 30huggingface.co/sylvia-xiao/IndexTTS_postrain

--- license: apache-2.0 language: - zh - ja - ms tags: - text-to-speech - tts - indextts pipeline_tag: text-to-speech --- # This is a brief introduction for model ckpts. ## original models: 1. bigvgan_discriminator.pth 2. bigvgan_generator.pth 3. bpe.model (tokenizer) 4. config.yaml (original inference configuration) 5. gpt.pth (backbone transformer) 6. dvae.pth (use for getting training audio tokens) 7. unigram_12000.vocab (tokenizer vocabulary) ## fine-tuned models: 1. Cantonese Model: a. config_yue.yaml b. gpt_tuned_yue.pth c. gpt_yue.pth (useless only for start stage in training) 2. Janpanese Model: a. config_ja.yaml b. gpt_tuned_ja.pth c. gpt_tuned_ja_v2.pth c. gpt_ja.pth (useless only for start stage in training) 3. Malaya Model: a. config_malay.yaml b. gpt_malaya_tuned.pth c. gpt_malay.pth (useless only for start stage in training)

NoteAug 30huggingface.co/sylvia-xiao/IndexTTS_postrain

Source context: 3 downloads · 0 likes · Pipeline text-to-speech · Repo sylvia-xiao/IndexTTS_postrain