Merge branch 'aberthe-main-patch-01221' into 'main'

README.md

@@ -1,92 +1,38 @@
-# Talking Car
+# Project Title: Talking car
 
-
-
-## Getting started
-
-To make it easy for you to get started with GitLab, here's a list of recommended next steps.
-
-Already a pro? Just edit this README.md and make it your own. Want to make it easy? [Use the template at the bottom](#editing-this-readme)!
-
-## Add your files
-
-- [ ] [Create](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#create-a-file) or [upload](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#upload-a-file) files
-- [ ] [Add files using the command line](https://docs.gitlab.com/ee/gitlab-basics/add-file.html#add-a-file-using-the-command-line) or push an existing Git repository with the following command:
-
-```
-cd existing_repo
-git remote add origin https://gitlab.uni.lu/360Lab/talking-car.git
-git branch -M main
-git push -uf origin main
-```
-
-## Integrate with your tools
-
-- [ ] [Set up project integrations](https://gitlab.uni.lu/360Lab/talking-car/-/settings/integrations)
-
-## Collaborate with your team
-
-- [ ] [Invite team members and collaborators](https://docs.gitlab.com/ee/user/project/members/)
-- [ ] [Create a new merge request](https://docs.gitlab.com/ee/user/project/merge_requests/creating_merge_requests.html)
-- [ ] [Automatically close issues from merge requests](https://docs.gitlab.com/ee/user/project/issues/managing_issues.html#closing-issues-automatically)
-- [ ] [Enable merge request approvals](https://docs.gitlab.com/ee/user/project/merge_requests/approvals/)
-- [ ] [Set auto-merge](https://docs.gitlab.com/ee/user/project/merge_requests/merge_when_pipeline_succeeds.html)
-
-## Test and Deploy
-
-Use the built-in continuous integration in GitLab.
-
-- [ ] [Get started with GitLab CI/CD](https://docs.gitlab.com/ee/ci/quick_start/index.html)
-- [ ] [Analyze your code for known vulnerabilities with Static Application Security Testing(SAST)](https://docs.gitlab.com/ee/user/application_security/sast/)
-- [ ] [Deploy to Kubernetes, Amazon EC2, or Amazon ECS using Auto Deploy](https://docs.gitlab.com/ee/topics/autodevops/requirements.html)
-- [ ] [Use pull-based deployments for improved Kubernetes management](https://docs.gitlab.com/ee/user/clusters/agent/)
-- [ ] [Set up protected environments](https://docs.gitlab.com/ee/ci/environments/protected_environments.html)
-
-***
-
-# Editing this README
-
-When you're ready to make this README your own, just edit this file and use the handy template below (or feel free to structure it however you want - this is just a starting point!). Thank you to [makeareadme.com](https://www.makeareadme.com/) for this template.
-
-## Suggestions for a good README
-Every project is different, so consider which of these sections apply to yours. The sections used in the template are suggestions for most open source projects. Also keep in mind that while a README can be too long and detailed, too long is better than too short. If you think your README is too long, consider utilizing another form of documentation rather than cutting out information.
-
-## Name
-Choose a self-explaining name for your project.
+A speaking assistant designed for in-car use, leveraging the LLaMA 2 model to facilitate vocal interactions between the car and its users. This notebook provides the foundation for a speech-enabled interface that can understand spoken questions and respond verbally, enhancing the driving experience with intelligent assistance.
 
 ## Description
-Let people know what your project can do specifically. Provide context and add a link to any reference visitors might be unfamiliar with. A list of Features or a Background subsection can also be added here. If there are alternatives to your project, this is a good place to list differentiating factors.
-
-## Badges
-On some READMEs, you may see small images that convey metadata, such as whether or not all the tests are passing for the project. You can use Shields to add some to your README. Many services also have instructions for adding a badge.
-
-## Visuals
-Depending on what you are making, it can be a good idea to include screenshots or even a video (you'll frequently see GIFs rather than actual videos). Tools like ttygif can help, but check out Asciinema for a more sophisticated method.
 
-## Installation
-Within a particular ecosystem, there may be a common way of installing things, such as using Yarn, NuGet, or Homebrew. However, consider the possibility that whoever is reading your README is a novice and would like more guidance. Listing specific steps helps remove ambiguity and gets people to using your project as quickly as possible. If it only runs in a specific context like a particular programming language version or operating system or has dependencies that have to be installed manually, also add a Requirements subsection.
+This project integrates speech-to-text and text-to-speech functionalities into a car's infotainment system, using the LLaMA 2 model to process and respond to vocal queries from users. It employs Gradio for user interface creation, NexusRaven for function calling, and integrates various APIs to fetch real-time information, making it a comprehensive solution for creating a responsive and interactive car assistant.
 
-## Usage
-Use examples liberally, and show the expected output if you can. It's helpful to have inline the smallest example of usage that you can demonstrate, while providing links to more sophisticated examples if they are too long to reasonably include in the README.
+## Features
 
-## Support
-Tell people where they can go to for help. It can be any combination of an issue tracker, a chat room, an email address, etc.
+•	Speech-to-Text and Text-to-Speech: Enables the car assistant to listen to spoken questions and respond audibly, providing a hands-free experience for drivers and passengers.  
+•	Intelligent Function Calling with NexusRaven: Implements a sophisticated system for executing commands and retrieving information based on user queries, using the LLaMA 2 model's capabilities.  
+•	Dynamic Model Integration: Incorporates multiple models for language recognition, speech processing, and text generation.  
+•	User-Friendly Gradio Interface: easy-to-use interface for testing and deploying the speaking assistant within the car's infotainment system.  
+•	Real-Time Information Retrieval: Capable of integrating with various APIs to provide up-to-date information on weather, routes, points of interest, and more.
 
-## Roadmap
-If you have ideas for releases in the future, it is a good idea to list them in the README.
+## Requirements
 
-## Contributing
-State if you are open to contributions and what your requirements are for accepting them.
+•	Gradio for creating interactive interfaces  
+•	Hugging Face Transformers and additional ML models for speech and language processing  
+•	NexusRaven for complex function execution  
+All required libraries and packages are directly loaded inside the notebook.
 
-For people who want to make changes to your project, it's helpful to have some documentation on how to get started. Perhaps there is a script that they should run or some environment variables that they need to set. Make these steps explicit. These instructions could also be useful to your future self.
+## Installation
 
-You can also document commands to lint the code or run tests. These steps help to ensure high code quality and reduce the likelihood that the changes inadvertently break something. Having instructions for running tests is especially helpful if it requires external setup, such as starting a Selenium server for testing in a browser.
+To set up the speaking assistant in your car's system, follow these steps:  
+1.	Run all the cells until the “Interfaces (text and audio)” section.  
+2.	Choose between the interfaces which one to run: audio-to-audio or text-to-text.  
+### Usage
+1.	Model Setup: Begin by loading the necessary models for speech recognition, language processing, and text-to-speech conversion as detailed in the "Models loads" section.  
+2.	Function Definition: Customize the assistant's responses and capabilities by defining functions in the "Function calling with NexusRaven" section.  
+3.	Interface Configuration: Choose the Gradio interface that suits your in-car system, following setup instructions in the "Interfaces (text and audio)" section.  
+4.	Activation: Execute one of the interface to start the speaking assistant, enabling vocal interactions within the car.  
 
 ## Authors and acknowledgment
-Show your appreciation to those who have contributed to the project.
-
-## License
-For open source projects, say how it is licensed.
 
-## Project status
-If you have run out of energy or time for your project, put a note at the top of the README saying that development has slowed down or stopped completely. Someone may choose to fork your project or volunteer to step in as a maintainer or owner, allowing your project to keep going. You can also make an explicit request for maintainers.
+Sasan Jafarnejad  
+Abigail Berthe--Pardo  

llama2.py

@@ -0,0 +1,86 @@
+# -*- coding: utf-8 -*-
+"""llama2
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/15UK6iHd1y0pMMQc-DbZIYhSteoTCUsMH
+"""
+
+#install and then restart execution
+!pip install accelerate
+!pip install bitsandbytes
+!pip install optimum
+!pip install auto-gptq
+
+!pip install transformers
+from transformers import AutoModelForCausalLM,AutoTokenizer
+import torch
+!pip install transformers huggingface_hub
+from huggingface_hub import notebook_login
+
+notebook_login()
+
+mn = 'stabilityai/StableBeluga-7B'
+#mn = "TheBloke/Llama-2-7b-Chat-GPTQ"
+
+model = AutoModelForCausalLM.from_pretrained(mn, device_map=0, load_in_8bit=True)
+
+#model = AutoModelForCausalLM.from_pretrained(mn, device_map=0, torch_dtype=torch.float16)
+
+sb_sys = "### System:\nYou are a AI driving assistant in my car, that follows instructions extremely well. Help as much as you can.\n\n"
+
+def gen(p, maxlen=15, sample=True):
+    toks = tokr(p, return_tensors="pt")
+    res = model.generate(**toks.to("cuda"), max_new_tokens=maxlen, do_sample=sample).to('cpu')
+    return tokr.batch_decode(res)
+
+tokr = AutoTokenizer.from_pretrained(mn)
+
+#to have a prompt corresponding to the specific format required by the fine-tuned model Stable Beluga
+def mk_prompt(user, syst=sb_sys): return f"{syst}### User: {user}\n\n### Assistant:\n"
+
+complete_answer= ''
+
+#attempt to get user location
+
+import requests
+
+response = requests.get("http://ip-api.com/json/")
+data = response.json()
+print(data['city'], data['lat'], data['lon'])
+city= data['city']
+lat = data['lat']
+lon = data['lon']
+
+import re
+model_answer= ''
+general_context= f'I am in my car in {city}, latitude {lat}, longitude {lon}, I can move with my car to reach a destination'
+pattern = r"Assistant:\\n(.*?)</s>"
+
+ques = "I hate pizzas"
+
+ques_ctx = f"""Answer the question with the help of the provided context.
+
+## Context
+
+{general_context} .
+
+## Question
+
+{ques}"""
+
+complete_answer = str(gen(mk_prompt(ques_ctx), 150))
+
+match = re.search(pattern, complete_answer, re.DOTALL)
+
+if match:
+    # Extracting the text
+    model_answer = match.group(1)
+else:
+    model_answer = "There has been an error with the generated response."
+
+general_context +=  model_answer
+print(model_answer)
+
+print(complete_answer)

stttotts.py

@@ -0,0 +1,177 @@
+# -*- coding: utf-8 -*-
+"""sttToTts.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/15QqRKFSwfhRdnaj5-R1z6xFfeEOOta38
+"""
+
+#text-to-speech and speech to text
+!pip install TTS
+!pip install transformers
+
+#text to speech
+from TTS.api import TTS
+tts = TTS("tts_models/multilingual/multi-dataset/your_tts", cs_api_model  = "TTS.cs_api.CS_API", gpu=True)
+
+#voice recording
+import IPython.display
+import google.colab.output
+import base64
+# all imports for voice recording
+from IPython.display import Javascript
+from google.colab import output
+from base64 import b64decode
+
+#to record sound, found on https://gist.github.com/korakot/c21c3476c024ad6d56d5f48b0bca92be
+
+RECORD = """
+const sleep  = time => new Promise(resolve => setTimeout(resolve, time))
+const b2text = blob => new Promise(resolve => {
+  const reader = new FileReader()
+  reader.onloadend = e => resolve(e.srcElement.result)
+  reader.readAsDataURL(blob)
+})
+var record = time => new Promise(async resolve => {
+  stream = await navigator.mediaDevices.getUserMedia({ audio: true })
+  recorder = new MediaRecorder(stream)
+  chunks = []
+  recorder.ondataavailable = e => chunks.push(e.data)
+  recorder.start()
+  await sleep(time)
+  recorder.onstop = async ()=>{
+    blob = new Blob(chunks)
+    text = await b2text(blob)
+    resolve(text)
+  }
+  recorder.stop()
+})
+"""
+
+def record(name, sec):
+  display(Javascript(RECORD))
+  s = output.eval_js('record(%d)' % (sec*1000))
+  b = b64decode(s.split(',')[1])
+  with open(f'{name}.webm','wb') as f:
+    f.write(b)
+  return (f'{name}.webm')  # or webm ?
+
+#to record the text which is going to be transcribed
+record('audio', sec = 10)
+
+#works -- speech-to-text with an audio I provide the path to reach
+from transformers import WhisperProcessor, WhisperForConditionalGeneration
+import librosa
+
+# load model and processor
+processor = WhisperProcessor.from_pretrained("openai/whisper-small")
+model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-small")
+model.config.forced_decoder_ids = None
+
+# load audio from a specific path
+audio_path = "audio.webm"
+audio_array, sampling_rate = librosa.load(audio_path, sr=16000)  # "sr=16000" ensures that the sampling rate is as required
+
+
+# process the audio array
+input_features = processor(audio_array, sampling_rate, return_tensors="pt").input_features
+
+
+predicted_ids = model.generate(input_features)
+
+transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+print(transcription)
+
+#to record the speaker's voice used for tts
+record('speaker', sec = 10 )
+
+#library to convert digits to words (ex : 1 --> one)
+import locale
+locale.getpreferredencoding = lambda: "UTF-8"
+!pip install inflect
+
+import re
+import inflect
+#because numbers under digit format are ignored otherwise
+def convert_numbers_to_words(s):
+    p = inflect.engine()
+    # Find all sequences of digits in the string
+    numbers = re.findall(r'\d+', s)
+    for number in numbers:
+        # Convert each number to words
+        words = p.number_to_words(number)
+        # Replace the original number in the string with its word representation
+        s = s.replace(number, words)
+    return s
+
+#model test 1 for text to speech
+#works - text to speech with voice cloner (by providing the path to the audio where the voice is)
+from google.colab import drive
+from IPython.display import Audio
+
+
+
+tts.tts_to_file(text=convert_numbers_to_words(str(transcription)),
+                file_path="output.wav",
+                speaker_wav='speaker.webm',
+                language="en",
+                emotion ='angry',
+                speed = 2)
+audio_path = "output.wav"
+Audio(audio_path)
+
+#model test 2 for text to speech
+from IPython.display import Audio
+# TTS with on the fly voice conversion
+api = TTS("tts_models/deu/fairseq/vits")
+api.tts_with_vc_to_file(
+    text="Wie sage ich auf Italienisch, dass ich dich liebe?",
+    speaker_wav="speaker.webm",
+    file_path="ouptut.wav"
+)
+audio_path = "output.wav"
+Audio(audio_path)
+
+#model test 3 for text to speech
+from TTS.api import TTS
+tts = TTS("tts_models/multilingual/multi-dataset/xtts_v1", gpu=True)
+
+from IPython.display import Audio
+
+
+# generate speech by cloning a voice using custom settings
+tts.tts_to_file(text="But for me to rap like a computer it must be in my genes I got a laptop in my back pocket My pen'll go off when I half-cock it Got a fat knot from that rap profit Made a livin' and a killin' off it Ever since Bill Clinton was still in office with Monica Lewinsky feelin' on his nutsack I'm an MC still as honest",
+                file_path="output.wav",
+                speaker_wav="Slide 1.m4a",
+                language="en",
+                emotion = "neutral",
+                decoder_iterations=35)
+
+audio_path = "output.wav"
+Audio(audio_path)
+
+# Init TTS with the target studio speaker
+tts = TTS(model_name="coqui_studio/en/Torcull Diarmuid/coqui_studio", progress_bar=False)
+# Run TTS
+tts.tts_to_file(text="This is a test.", file_path=OUTPUT_PATH)
+# Run TTS with emotion and speed control
+tts.tts_to_file(text="This is a test.", file_path=OUTPUT_PATH, emotion="Happy", speed=1.5)
+
+#model test 4 for text to speech
+from IPython.display import Audio
+
+from TTS.api import TTS
+#api = TTS(model_name="tts_models/eng/fairseq/vits").to("cuda")
+#api.tts_to_file("This is a test.", file_path="output.wav")
+
+# TTS with on the fly voice conversion
+api = TTS("tts_models/deu/fairseq/vits")
+api.tts_with_vc_to_file(
+    "I am a basic human",
+    speaker_wav="speaker.webm",
+    file_path="output.wav"
+)
+
+audio_path = "output.wav"
+Audio(audio_path)