juancopi81 / ml-with-audio

HF's ML for Audio study group

Hugging Face Machine Learning for Audio Study Group

Welcome to the ML for Audio Study Group. Through a series of presentations, paper reading and discussions, we'll explore the field of applying Machine Learning in the Audio domain. Some examples of this are:

• Generating synthetic sound out of a given text (think of conversational assistants)
• Transcribing audio signals to text.
• Removing noise out of an audio.
• Separating different sources of audio.
• Identifying which speaker is talking.
• And much more!

We suggest you to join the community Discord at http://hf.co/join/discord, and we're looking forward to meet at the #ml-4-audio-study-group channel 🤗. Remember, this is a community effort so make out of this your space!

Organisation

We'll kick off with some basics and then collaboratively decide the further direction of the group.

Before each session:

• Read/watch related resources

During each session, you can

• Ask question in the forum
• Present a short (~10-15mins) presentation on the topic (agree beforehand)

Before/after:

• Keep discussing/asking questions about the topic (#ml-4-audio-study channel on discord)
• Share interesting resources

Schedule

Date	Topics	Resources (To read before)
Dec 14, 2021	Kickoff + Overview of Audio related usecases (video, questions)	The 3 DL Frameworks for e2e Speech Recognition that power your devices
Dec 21, 2021	Intro to Audio Automatic Speech Recognition Deep Dive (video, questions)	Intro to Audio for FastAI Sections 1 and 2 Speech and Language Processing 26.1-26.5
Jan 4, 2022	Text to Speech Deep Dive (video, questions)	Intro to Audio & ASR Notebooks Speech and Language Processing 26.6
Jan 18, 2022	pyctcdecode: A simple & fast STT prediction decoding algorithm (demo, slides, questions)	Beam search CTC decoding pyctcdecode

Supplementary Resources

In case you want to solidify a concept, or just want to go down further deep into the speech processing rabbit-hole.

General Resources

• Slides from LSA352: Slides (no videos available)
• Slides from CS224S (Latest): Slides (no videos available)
• Speech & Language Processing Book (Chapters 25 & 26) - E-book

Research Papers

• Speech Recognition Papers: Github repo
• Speech Synthesis Papers: Github repo

Toolkits

• Speechbrain - Github repo
• Toucan - Github repo
• ESPnet - Github repo

Demos

• Add interesting effects to your audio files - Huggingface spaces
• Generate Speech from text (TTS) - Huggingface spaces
• Generate text from Speech (ASR) - Huggingface spaces