Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
drbaph
/
CSM-1B
like
2
Text-to-Speech
Safetensors
English
model_hub_mixin
pytorch_model_hub_mixin
License:
apache-2.0
Model card
Files
Files and versions
Community
main
CSM-1B
/
config.json
drbaph
Upload 2 files
7716963
verified
about 2 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
155 Bytes
{
"audio_num_codebooks"
:
32
,
"audio_vocab_size"
:
2051
,
"backbone_flavor"
:
"llama-1B"
,
"decoder_flavor"
:
"llama-100M"
,
"text_vocab_size"
:
128256
}