Whisper
AI
speech recognition
SHOW HN2022
How HN took it
29 positive, 21 neutral or asking, 2 mixed, 4 critical, out of 56 comments about the project. Thread score +0.46.
Idea: 9 for, 2 againstPerformance: 5 for, 1 againstExecution: 4 for, 0 againstDesign: 3 for, 0 againstDocs: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Fast CPU inference, no dependencies, easy to build
From 3 comments
Offline models, especially speech recognition, is a game changer for many apps. A fully CPU based implementation, simple enough with minimal dependencies is also something that…
stephc_int13 on HNWorks well on my old Intel 2020 Macbook Pro. Having no dependencies meant I was able to just clone the repo and build (as long as you have the C++ tooling). There's something…
klim2media on HNReally amazing work - just cloned the repo on my Apple Silicon Mac and ran the streaming sample. Worked flawlessly.
iamflimflam1 on HN
Enables offline speech recognition and accessibility uses
From 2 comments
I've been watching this repo pretty much since the beginning, and the amount of work you've achieved is incredible. I've started tinkering with the code about last week and…
gdz on HNOffline models, especially speech recognition, is a game changer for many apps. A fully CPU based implementation, simple enough with minimal dependencies is also something that…
stephc_int13 on HN
Clean, minimal codebase
From 2 comments
Great work. It's a real bowl of fresh air coming from huge framework that use cuda. So many different cuda version, with each framework using its own, that all rely on a…
GistNoesis on HNI've been watching this repo pretty much since the beginning, and the amount of work you've achieved is incredible. I've started tinkering with the code about last week and…
gdz on HN
Objections
Not clearly better than built-in or other open-source speech models
From 1 comment
There are tons of open source STT models, what makes whisper so valuable? I especially don't get it on mobile, where the native STT built into the OS is now real-time and…
jarbus on HN
Greedy decoder gives more mistakes than beam search
From 1 comment
I have only implemented the Greedy decoder which is worse compared to the BeamSearch decoder in most cases.
ggerganov on HN
Mixed C/C++ naming criticized as not a real language
From 1 comment
There is no language called "C/C++". If, to use it, you need C++, it's a C++ system, period. If parts are in C, that is an implementation detail, and is furthermore pointless;…
moloch-hai on HN
Requests
Speaker identification in output
From 1 comment
This is really awesome, great work! I downloaded a long video from YouTube that is very challenging to transcribe (it is an interview with Hayek, who was both very soft spoken…
eigenvalue on HN
Built-in audio format conversion via ffmpeg
From 1 comment
This is really awesome, great work! I downloaded a long video from YouTube that is very challenging to transcribe (it is an interview with Hayek, who was both very soft spoken…
eigenvalue on HN
Feature roadmap
From 1 comment
Is there a feature roadmap? OpenAI quietly launched Whisper V2 https://news.ycombinator.com/item?id=33884716
password4321 on HN
Questions
GPU or Neural Engine support
From 2 comments
This is really cool, and I have been meaning to get my hands dirty with Whisper I looks like you’ve definitely maximized the parallelization on the CPU/AMX here, but have you…
conradev on HNIs there any improvement to GPU inference at all? CPU inference is not cost effective for my use-case
fareesh on HN
How to deploy in a web app
From 1 comment
How could I deploy and use this in my web app? I don't know much about Web Assembly if someone can ELI5 please thanks. Is the result some API that I send requests to? Thanks a ton!
TheEndIsNigh on HN
Confidence levels for restricted vocabulary
From 1 comment
Hi Georgi, I am experimenting with your code now. Is there a way to force Whisper to only consider a limited vocabulary and then respond with confidence levels? I am working on…
wfcollins on HN
Alternatives named
PyTorch Whisper implementation
From 1 comment
> about 2-3 times faster compared to the current PyTorch implementation This is surprising to me. Is this about CPU only? Then it would make sense.
sva_ on HN
tinygrad
From 1 comment
Awesome work. Curious whether the whisper model could be ported to tinygrad and how the performance would compare to your implementation.
vletal on HN
Built-in OS speech recognition
From 1 comment
There are tons of open source STT models, what makes whisper so valuable? I especially don't get it on mobile, where the native STT built into the OS is now real-time and…
jarbus on HN