A 1B speech-generation model capable of receiving texts and audio as inputs. A bigger, fine-tuned version of the model went viral for its quality (see blog post too).
Specs
Params1B
LicenseApache-2.0
Adoption · Hugging Face
RAM score
Relative Adoption Metric not applicable.
Hugging Face Downloads
115K
last 30d
2.1M
all time
HF Likes
2.5K
Relative Adoption Metric not applicable.
Related Models
