| #! /usr/bin/env python | |
| # -*- coding: utf-8 -*- | |
| """This module's docstring summary line. | |
| This is a multi-line docstring. Paragraphs are separated with blank lines. | |
| Lines conform to 79-column limit. | |
| Module and packages names should be short, lower_case_with_underscores. | |
| Notice that this in not PEP8-cheatsheet.py | |
| Seriously, use flake8. Atom.io with https://atom.io/packages/linter-flake8 | |
| is awesome! | |
| See http://www.python.org/dev/peps/pep-0008/ for more PEP-8 details |
| import pandas as pd | |
| from sqlalchemy import create_engine | |
| import cx_Oracle | |
| oracle_connection_string = ( | |
| 'oracle+cx_oracle://{username}:{password}@' + | |
| cx_Oracle.makedsn('{hostname}', '{port}', service_name='{service_name}') | |
| ) | |
| engine = create_engine( |
| # Credits: https://scipython.com/book/chapter-8-scipy/additional-examples/the-sir-epidemic-model/ | |
| import numpy as np | |
| from scipy.integrate import odeint | |
| import matplotlib.pyplot as plt | |
| import seaborn as sns | |
| # Total population, N. | |
| N = 1339200000 |
| %matplotlib inline | |
| import numpy as np | |
| from scipy.integrate import odeint | |
| import matplotlib.pyplot as plt | |
| # Total population, N. | |
| N = 1339200000 | |
| # Initial number of infected and recovered individuals, I0 and R0. |
Whilst the current ASR landscape is really promosing a lot of it is currently benchmarked on rather "clean" datasets. This often creates a false sense of confidence in the Architecture which might not translate to the real world.
Hey hey!
We are on a mission to democratise speech, increase the language coverage of current SoTA speech recognition and push the limits of what is possible. Come join us from December 5th - 19th for a community sprint powered by Lambda Labs. Through this sprint, we'll cover 70+ languages, 39M - 1550M parameters & evaluate our models on real-world evaluation datasets.
Register your interest via the Google form here.
The goal of the sprint is to fine-tune Whisper in as many languages as possible and make them accessible to the community. We hope that especially low-resource languages will profit from this event.
| user_name= | |
| ssh_key="" | |
| cd /home | |
| sudo useradd -m "$user_name" | |
| sudo mkdir /home/"$user_name"/.ssh | |
| echo "$ssh_key" | sudo tee -a /home/"$user_name"/.ssh/authorized_keys | |
| sudo chsh -s /usr/bin/bash "$user_name" | |
| curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | sudo bash | |
| sudo apt-get install git-lfs |
| #pip install git+https://github.com/huggingface/transformers.git | |
| import datetime | |
| import sys | |
| from transformers import pipeline | |
| from transformers.pipelines.audio_utils import ffmpeg_microphone_live | |
| pipe = pipeline("automatic-speech-recognition", model="openai/whisper-base", device=0) | |
| sampling_rate = pipe.feature_extractor.sampling_rate |
| # Load the dataset (locally) | |
| from datasets import load_dataset | |
| cv_11 = load_dataset("mozilla-foundation/common_voice_11_0", "hi", split="train") | |
| # Stream the dataset | |
| from datasets import load_dataset |
| !pip install transformers optimum | |
| !pip install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| model_name_or_path = "TheBloke/zephyr-7B-beta-GPTQ" | |
| model = AutoModelForCausalLM.from_pretrained(model_name_or_path, | |
| device_map="auto", | |
| trust_remote_code=False, |
