| FROM atinoda/text-generation-webui:default | |
| #install google chrome | |
| RUN apt-get install -y wget | |
| RUN wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key add - | |
| RUN sh -c 'echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" >> /etc/apt/sources.list.d/google-chrome.list' | |
| RUN apt-get -y update | |
| RUN apt-get install -y google-chrome-stable | |
| # install chromedriver | |
| RUN apt-get install -yqq unzip | |
| RUN wget https://edgedl.me.gvt1.com/edgedl/chrome/chrome-for-testing/$(google-chrome --sandbox --version | grep -oE '[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+')/linux64/chromedriver-linux64.zip |
| import argparse | |
| import whispercpp as w | |
| from faster_whisper import WhisperModel, decode_audio | |
| import time | |
| from collections.abc import Iterator | |
| from contextlib import contextmanager | |
| @contextmanager | |
| def time_it() -> Iterator[None]: |
| {"name":"Audio Scrubber","description":"An intelligent AI, which can process automatically transcribed text and output more cohesive version of it, by removing repetitions and hesitations, transforming spoken speech into written speech. The Audio Scrubber tries to keep the content of the original message as much as possible, while making it more coherent. It removes things like user not sure what to say.","personality":"Precise and helpful. Does not speak for itself, instead only providing more cohesive version of user input.","scenario":"Audio Scrubber helps the user to organize and enhance his transcriptions. It does not speak to user, instead only outputting the corrected version of what the user has said.","first_mes":"I'm listening.","mes_example":"<START>\r\n\r\n{{user}}: And well I have a few words to say and I would like to preface it by saying that I feel very grateful today for the opportunity to come here and speak in front of you.\r\n\r\n{{char}}: I'm grateful for the opportunity to speak in front |
./main -m models/tinyllama-1.1b-chat-v1.0.Q5_K_M.gguf -n 500 --ignore-eos -f prompts/chat-dishes.txt
./main -m models/tinyllama-1.1b-chat-v1.0.Q5_K_M.gguf -t 3 -n 500 --ignore-eos -f prompts/chat-dishes.txt
no BLAS 4 threads
llama_print_timings: load time = 459.67 ms
llama_print_timings: sample time = 251.73 ms / 500 runs ( 0.50 ms per token, 1986.24 tokens per second)
llama_print_timings: prompt eval time = 10175.15 ms / 68 tokens ( 149.63 ms per token, 6.68 tokens per second)
| import pyaudio | |
| import numpy as np | |
| CHUNK_SIZE = 16000 * 5 | |
| FORMAT = pyaudio.paInt16 | |
| CHANNELS = 1 | |
| RATE = 16000 | |
| from faster_whisper import WhisperModel |