syncabook VS whisper

Amazing! I've made a similar ebooks-audiobooks aligner years ago: https://github.com/r4victor/syncabook. At that time, I chose to synthesize the text and align two audio sequences because I found texts-alignment approaches (including ML-based ones) too compute-intensive and inadequate for long texts. I see Storyteller works by aligning the texts. Could you give some view on how long it takes to sync a book?

Also, my experience was that audio and text versions are often very different (e.g. the audio having an intro missing from the text). It'd very interesting to know how well Storyteller handles such cases. Does it require manual audio/text editing or handle the differences automatically?

Unfortunaly, this audiobook isn't synchorized to the text on Kindle. So, in order to synchronize the epub and audio myself, initially, I tried using syncabook, but the results weren't great for some reason. I then tried using OpenAI's Whisper to generate the text from the audio. This might've given decent results, but ultimately I decided I wanted to keep the book's formatting (paragraphs, emphasis, etc.)

I've tried syncabook, but that didn't help. I've tried whisperX, to get word-level timings, but the results are pretty bad/unusable.

From searching a bit I found https://github.com/r4victor/syncabook this might help anyone intrigued about the idea. I suspect this is the tool you're talking about? Your post is really a long form question, and could have been a lot shorter.

This software can generate epubs with audio completely automatically for a lot of simpler languages. The problem is it doesn't support Japanese.

Let’s not talk about local models as the hardware requirements are way beyond most of these people’s reach. I have a MacBook Air with an M2 chip and 8GB of RAM and can hardly run Whisper locally, so I use this HuggingFace space.

Last week, I launched notesGPT, a free and open source voice note app that has 35,000 visitors, 7,000 users, and over 1,000 GitHub stars so far in the last week. It allows you to record a voice note, transcribes it uses Whisper, and uses Mixtral via Together to extract action items and display them in an action items view. It’s also fully open source and comes equipped with authentication, storage, vector search, action items, and is fully responsive on mobile for ease of use.

I found a pretty good discussion in the topic here:

https://github.com/openai/whisper/discussions/1243

There is a plot of language performance on their repo: https://github.com/openai/whisper

I am not aware of a multi-lingual leaderboard for speech recognition models.

I don't know how OP does it, but here's how I'd do it:

* Generate a transcript by runing Whisper against the podcast audio file: https://github.com/openai/whisper

* Upload transcript to ChatGPT and ask it to summarize.

* Automate all the above.

Ahh, that makes sense. I've been building something like that, but only from other languages into English using Whisper

Whisper already generates subtitles[0], supporting VTT and SRT so this is just a thin wrapper around that.

[0]: https://github.com/openai/whisper/blob/e58f28804528831904c3b...

> although it does require you to wear headphones so the bot doesn't hear itself and get interrupted.

Maybe you can rely on some sort of speaker identification to sort this out?

https://github.com/openai/whisper/discussions/264