Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: LibreASR – An On-Premises, Streaming Speech Recognition System

github.com

Post reply on HN
Print view View original

21–30 of 73 posts

Re: Show HN: LibreASR – An On-Premises, Streaming Speech Recognition System

#21

Post by guillem_lefait »

Nice project and bold to demo with a French native speaking English.

On a side project, I'm looking at the best interface to facilitate further edition (correction) of the recognized text. Target is local councils and regional parliament, where sessions are usually recorded but without transcripts. If xx% accuracy is enough to identify keywords, manual edition is still required to not distort precise meaning.

Nothing special in the interface, but two features seems interesting: 1. Be able to collaborate in real-time. Maybe using Etherpad API to merge multiple editions. 2. Easily validate text and label speakers so as to generate new training data.

Pointers to similar existing solutions would be very appreciated.

Re: Show HN: LibreASR – An On-Premises, Streaming Speech Recognition System

#22

Post by fareesh »

Is there an open-source or paid SDK/API that I can use to create a group voice chat mobile app with "live" transcription? Or something that can plug-in to a system like this?

I looked at Twilio but they seem to only offer a means to do it on their VOIP/SIP product.

Re: Show HN: LibreASR – An On-Premises, Streaming Speech Recognition System

#23

Post by bravura »

blackcat201 wrote: post #12

Cool project, seems like your model have similar WER as mine (4th reference in readme). Do you plan to do any pre-training on the encoder part in the future? Maybe something like this[1] [1] https://ai.facebook.com/blog/wav2vec-20-learning-the-structu...

Hey black cat, I have some work in preprint for a NeuroIPS workshop, demonstrating negative results of different audio distances on pitch tasks. There is one particular w2v result I'd like your feedback on.

Do you mind emailing me? Lastname at gmail dot com (see my profile for my name)

Re: Show HN: LibreASR – An On-Premises, Streaming Speech Recognition System

#24

Post by the_biot »

iceychris wrote: post #4

Hey HN! I've been working on this for a while now. While there are other on-premise solutions using older models such as DeepSpeech [0], I haven't found a deployable project supporting multiple languages using the recent RNN-T Architecture [1]. Please note that this does not achieve SotA performance. Also, I've only trained it on one GPU so there might be room for improvement. Edit: Don't expect good performance :D t…

Why on earth would you put a demo front and center that shows your software doing a terrible, terrible job?

Re: Show HN: LibreASR – An On-Premises, Streaming Speech Recognition System

#25

Post by brmgb »

the_biot wrote: post #24
iceychris wrote: post #4

Hey HN! I've been working on this for a while now. While there are other on-premise solutions using older models such as DeepSpeech [0], I haven't found a deployable project supporting multiple languages using the recent RNN-T Architecture [1]. Please note that this does not achieve SotA performance. Also, I've only trained it on one GPU so there might be room for improvement. Edit: Don't expect good performance :D t…

Why on earth would you put a demo front and center that shows your software doing a terrible, terrible job?

That's called setting up expectations. If you know your project might interest people but needs work, why pretends it's good when it's not? They seem to be courting contributors more than users anyway.

I found the video to be funny. It nicely highlights both the current limitations and the ambition of the projects. Bold choice certainly but I think it works.

Re: Show HN: LibreASR – An On-Premises, Streaming Speech Recognition System

#26

Post by nsomaru »

guillem_lefait wrote: post #21

Nice project and bold to demo with a French native speaking English. On a side project, I'm looking at the best interface to facilitate further edition (correction) of the recognized text. Target is local councils and regional parliament, where sessions are usually recorded but without transcripts. If xx% accuracy is enough to identify keywords, manual edition is still required to not distort precise meaning. Nothing…

I’m really interested in this project too. Been thinking about similar solutions for a while now.

I looked into Kaldi and Mozilla Deep Speech but the former seems geared at ASR experts and the latter didn’t seem suited for my particular application (longer recorded audio or real time stream)

Re: Show HN: LibreASR – An On-Premises, Streaming Speech Recognition System

#27

Post by th3h4mm3r »

iceychris wrote: post #4

Hey HN! I've been working on this for a while now. While there are other on-premise solutions using older models such as DeepSpeech [0], I haven't found a deployable project supporting multiple languages using the recent RNN-T Architecture [1]. Please note that this does not achieve SotA performance. Also, I've only trained it on one GPU so there might be room for improvement. Edit: Don't expect good performance :D t…

Hi! What should you need to implement other language i.e. Italian or French? I mean: it's a problem due to the less of datas or what?

Another question: could you use for example mozilla voice data to train/test?

Re: Show HN: LibreASR – An On-Premises, Streaming Speech Recognition System

#28

Post by iceychris »

th3h4mm3r wrote: post #27
iceychris wrote: post #4

Hey HN! I've been working on this for a while now. While there are other on-premise solutions using older models such as DeepSpeech [0], I haven't found a deployable project supporting multiple languages using the recent RNN-T Architecture [1]. Please note that this does not achieve SotA performance. Also, I've only trained it on one GPU so there might be room for improvement. Edit: Don't expect good performance :D t…

Hi! What should you need to implement other language i.e. Italian or French? I mean: it's a problem due to the less of datas or what? Another question: could you use for example mozilla voice data to train/test?

Data and compute are the largest hurdles. I only have one GPU and training one model takes 3+ days, so I am limited by that. Also, scraping from YouTube takes time and a lot of storage (multiple TBs).

Mozilla Common Voice data is already used for training.

Re: Show HN: LibreASR – An On-Premises, Streaming Speech Recognition System

#29

Post by jack_pp »

iceychris wrote: post #28
th3h4mm3r wrote: post #27

Earlier quoted context omitted.

Hi! What should you need to implement other language i.e. Italian or French? I mean: it's a problem due to the less of datas or what? Another question: could you use for example mozilla voice data to train/test?

Data and compute are the largest hurdles. I only have one GPU and training one model takes 3+ days, so I am limited by that. Also, scraping from YouTube takes time and a lot of storage (multiple TBs). Mozilla Common Voice data is already used for training.

Why does it take a lot of data? Afaik you can select lower quality in youtube-dl but you don't even need video do you?

Re: Show HN: LibreASR – An On-Premises, Streaming Speech Recognition System

#30

Post by th3h4mm3r »

iceychris wrote: post #28
th3h4mm3r wrote: post #27

Earlier quoted context omitted.

Hi! What should you need to implement other language i.e. Italian or French? I mean: it's a problem due to the less of datas or what? Another question: could you use for example mozilla voice data to train/test?

Data and compute are the largest hurdles. I only have one GPU and training one model takes 3+ days, so I am limited by that. Also, scraping from YouTube takes time and a lot of storage (multiple TBs). Mozilla Common Voice data is already used for training.

So do you scrap videos from youtube with subtitles to collect data?
Post reply on HN