Hugging Face's logo

facebook
/
seamless-m4t-v2-large

Automatic Speech Recognition
Transformers
Safetensors
seamless_m4t_v2
feature-extraction
audio-to-audio
text-to-speech
seamless_communication
Model card Files
xet
 Community
59

Questions on the model capabilities and features

#50
by yevgeniyilyin - opened
Discussion
yevgeniyilyin

We started a PoC with this model and there are couple of question we weren't able to find answer in the documentation:

  1. Is there an option to generate a female voice?
  2. Is there any options to do tuning using tags for: talking speed, declinations, correct pronunciation of currencies and dates, higher or lower voice pitch. Any mechanisms to achieve this with the model?

Sign up or log in to comment