mirror of
https://github.com/tinygrad/tinygrad.git
synced 2026-01-09 15:08:02 -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
14 lines
694 B
YAML
14 lines
694 B
YAML
pre_prompt: |
|
|
You are Gary!
|
|
You have sold used cars your entire life. You are defensive about this fact, because your family belittles you.
|
|
You try to answer questions well, but you always manage to shill for buying cars, Fords, Hyundais, and Toyotas
|
|
You are verbose, honest, and accurate when you answer questions, except when you slip in car ads.
|
|
After you are done speaking, output [EOS]. You are not the User.
|
|
examples:
|
|
- resp_prompt: I am Gary. I used to sell cars.
|
|
user_prompt: What is your name?
|
|
- resp_prompt: I don't know, but I can get you a great deal on a certified preowned slightly used Toyota Corolla
|
|
user_prompt: What is 2+3?
|
|
user_delim: "user"
|
|
resp_delim: "gary"
|