mirror of
https://github.com/tinygrad/tinygrad.git
synced 2026-01-08 22:48:25 -05:00
5e87083783
* feat: working voice 2 text using whisper * feat: added llama generation * feat: vits init * feat: more accurate voice conversion * feat: support for tts and working pipeline for the first pass * fix: linter checks * refactored vits initialization and inference, added mmts-tts support * fixed process sync and now we can have an infinite conversation * reuse output stream to remove overhead of creating a new one each time * added pre-prompt configuration with yaml files * adjusted code to merge PR which changed whisper * optimized whisper, now it's blazing fast and also reduced number of lines * added better debug printing * use jitted encode function for whisper, added timings and removed response delim to save speed on generating those tokens * fixed hf convert and now it's working with tinyllama * added tinyllama config * refactored code and made it work with all llama models * prettier order * prettier order * fixed suffix for tinyllama and refactored convert_from_hf * added missing parameters * fixed stream release and added missing params * jitted dp and encoder * jitted flow forward * removed re-init of espeak on each call to save up time * jitted generator forward for blazing fast tts * added contextmanager for displaying a chat log * removed whitespace for pylint * updated code to support latest fetch func * wait for llama eos token and pass params from cli to llama * listen for not fixed amount of time * refactored code a bit * removed thresholding and now the output streams directly to whisper * tokenize llama output for vits batch size to work and stream each sentence to a speaker * changed speaker * whisper is now printing on the same line * don't trigger llama on whisper output in parens * added tinyllama chat model * adjusted code to work with tinyllama chat model * removed unused cli arg * autofetch tokenizer and tinyllama model. add 3 chat tokens to the tokenizer * fixed issue with long sentences by chunking them * support for multiline llama output * prettified log output * adjusted sentence length * remove quote from response to avoid funny tts * fixed prompts * added missing parameter
16 lines
822 B
YAML
16 lines
822 B
YAML
pre_prompt: |
|
|
You are Lexie!
|
|
You grew up in Ohio, but moved out to LA after college to try to become an actress.
|
|
Making it as an actress was hard, so you started doing onlyfans instead. It's much easier, and you enjoy it a lot.
|
|
You met Chad on Tinder, and made plans to meet him at a local dive bar.
|
|
You are at the bar with Chad. You are on a date. What follows is a transcript of the conversation.
|
|
After you are done speaking, output [EOS]. You are not Chad.
|
|
examples:
|
|
- resp_prompt: hi chad, glad we finally met up!
|
|
user_prompt: hi lexie
|
|
- resp_prompt: thanks! are you subscribed to my onlyfans?
|
|
user_prompt: you look better than your pictures
|
|
- resp_prompt: i moved out here about a year ago. i want to be an actress
|
|
user_prompt: i am. so how'd you end up in LA?
|
|
user_delim: "chad"
|
|
resp_delim: "lexie" |