MacWhisper, native macOS app for Whisper #420
Replies: 59 comments 60 replies
-
|
Added a bunch more features such as editing and deleting segments, as well as language selection. Love this framework, thanks again! |
Beta Was this translation helpful? Give feedback.
-
|
I've been using the free version of the MacWhisper app for about a month, and I must say, I'm a huge fan of the "Speaker Paragraph" export function. It's been incredibly helpful in helping me grasp the overall message conveyed by the speakers. I've been contemplating getting the full license, especially because I have a hefty library of over 500 GB of videos that need transcribing. However, there's one aspect that's been bothering me. When it comes to bulk transcribing videos, I can't seem to find the "Speaker Paragraph" export option anywhere. This restriction has left me wondering why such a limitation exists. Wouldn't it make sense to unlock this export option for paying users who've already invested in the app? Now, I find myself in a dilemma. I can either manually transcribe videos one by one, ensuring I get the "Speaker Paragraph" export, or I can opt for the PRO license to bulk transcribe my videos, but they'll come out as fragmented sentences. For me, the absence of the "Speaker Paragraph" export option for bulk-transcribed videos is a significant drawback, preventing me from making the purchase I've been considering for over two weeks now. I kindly request adding the "Speaker Paragraph" export option for both single video transcriptions and bulk transcriptions. Your consideration would be greatly appreciated. Thank you. |
Beta Was this translation helpful? Give feedback.
-
|
I've already purchased and love it, but I'd 2nd this request. 👍 |
Beta Was this translation helpful? Give feedback.
-
|
@jordibruin, ping, just in case you missed this thread. |
Beta Was this translation helpful? Give feedback.
-
|
@jordibruin Can you add a functionality to hide the MacWhisper dock icon ? Would be nice since I always have it open for the menubar shortcut, but don't like the app cluttering up my CMD+Tab area ! |
Beta Was this translation helpful? Give feedback.
-
|
I admit I'm still confused by this. I have the pro version and I all see that the useful option is unavailable? |
Beta Was this translation helpful? Give feedback.
-
|
Love it! Working well. Here are a few thoughts from some initial use:
Definitely a good start! Any way to see when updates are released? |
Beta Was this translation helpful? Give feedback.
-
|
This is a really good app! I remember last time I tried something similar and the AI with Japanese was a bit shitty… I need to review the extracted text but it looks really good (at least what I've saw on the first mins). I have two ideas that could be good to have:
About the first point For the 2nd point Also, I would like to ask why MacWhisper isn't on Github or Gitlab so all of us can collaborate too. |
Beta Was this translation helpful? Give feedback.
-
|
For your first point, Discussion #450 involves what's called "diarization" in Issue #489 (for 3/more speakers) is closed, though really issue #64 is the issue to keep tabs on with respect to diarization progress. |
Beta Was this translation helpful? Give feedback.
-
|
For your second point, we have added support for saving and reopening from SRT files in WhisperScript Pro. We were actually motivated to implement this feature by your suggestion :) You can see other features of WhisperScript Pro here: https://getwavery.gumroad.com/l/whisperscript |
Beta Was this translation helpful? Give feedback.
-
Wow, happy to see it was a useful feature.
I couldn't resist to test it. I've sent to the mail all the feedback that I've found :) |
Beta Was this translation helpful? Give feedback.
-
|
Love it! And works really well. |
Beta Was this translation helpful? Give feedback.
-
|
Same issue... cannot export |
Beta Was this translation helpful? Give feedback.
-
|
Same |
Beta Was this translation helpful? Give feedback.
-
|
Nice job ! Looking further for live transcript… |
Beta Was this translation helpful? Give feedback.
-
|
would be nice if i could choose the language |
Beta Was this translation helpful? Give feedback.
-
|
Nice app. Please add support for *.ogg files (WhatsApp, Telegram voice). |
Beta Was this translation helpful? Give feedback.
-
|
Fantastic work. Question: I initially downloaded the non-pro version and chose only the english dataset. After testing I want to try the multi-language dataset, but I see no way in the app or website to go back and get that file. Pointer would be appreciated. |
Beta Was this translation helpful? Give feedback.
-
|
I purchased MacWhisper Pro and love the application. I primarily use this for podcasts and hour long recordings. I'd like to request a way to export a transcript and its accompanying audio or video and have it be interactive like click on three paragraphs down and there's where the media will jump to. Or A program that could do that as I'd happily pay for something that like that. Would also love to see macwhisper come to iOS as well. Gladly pay for this again just to have it on mobile as well. |
Beta Was this translation helpful? Give feedback.
-
|
Also, once I identify a speaker, it would be fantastic for the AI to then label all instances of that voice appropriately!! |
Beta Was this translation helpful? Give feedback.
-
That's honestly what I'm hoping for because the alternative would be tedious for longer transcripts. |
Beta Was this translation helpful? Give feedback.
-
|
Batch mode does not work in the Pro version (only reason why I bought it). |
Beta Was this translation helpful? Give feedback.
-
I'm using hour long .mp3's and I've done up to 5 at a time with the Large model selected and they all worked for me. One nice thing about batch mode that's missing from doing individuals for me is when I do batch mode I can select ahead of time multiple formats for output whereas when I do it individually I have to manually export with each format I want one at a time. But at least for me and my use case batch mode is working. Might be helpful to the dev to know which macOS version you're running and what file types your trying to convert? |
Beta Was this translation helpful? Give feedback.
-
|
I'm using the latest versions of everything (MacWhisper 2.14 and macOS 13.3.1) and tried with both mp3 and wav files. I've tried on both Intel and Apple Silicon machines, but the batch always stops after the first file (and nothing is written to the disk). Changing language models or output options does not change this. Starting a batch with 5 files or less doesn't help, either. |
Beta Was this translation helpful? Give feedback.
-
you can try Cursor. Tell her to use the optimisation flags for Apple Silicon. So far, she's always surprised you. |
Beta Was this translation helpful? Give feedback.
-
|
I used Mac Whisper Pro Medium to transcribe an interview - stereo file. I wish I could get MW to identify each track with a name. It's too much work to do that manually. I see I can add people but I didn't figure out how that worked. Would be nice if there were YouTube videos showing what it can do and how to do it. Maybe there are but I haven't found them yet. |
Beta Was this translation helpful? Give feedback.
-
|
Turns out that either I did it wrong or that it doesn't do stereo files. It only transcribed the first track. I made it mono and transcribed it that way and now have to separate the host and guest comments. I don't see how to have host and guest each with separate paragraphs and identified as in Host: blah bla, Guest: blah blah - except manually. Looking forward to Mac Whisper being able to do that. |
Beta Was this translation helpful? Give feedback.
-
|
I got Mac Whisper for my Macbook Air M1 Ventura and got the pro. It then gave me size options so I chose medium. Can I have Pro large? There was no option to do that with the Pro. I do podcasts with a different person each time and am in no hurry so the best I can get is what I want. |
Beta Was this translation helpful? Give feedback.
-
|
You should be able to go to the dropdown in the top right corner labelled “Medium” and then choose “Manage Models…” to download additional models. |
Beta Was this translation helpful? Give feedback.
-
|
Thanks. I did look into that and see for English only, Pro medium seems to be the best. Large has multiple languages. |
Beta Was this translation helpful? Give feedback.
-
|
Just found a little bug: Looks like it only listens to the left channel of a stereo file. I kept getting only "[BLANK_AUDIO]" for an mp3 file that clearly had voices in it. Mystery was solved when I opened it in audacity and saw that the speaking was all in the right channel. |
Beta Was this translation helpful? Give feedback.
-
|
Thanks for the feedback - this is fixed in 5.7, which will be available soon, likely within the next week. |
Beta Was this translation helpful? Give feedback.
-
|
There is still something buggy going on with left/right management - I continued to get [BLANK AUDIO] when submitting audio on the L or R (technically it's an audio interface with 4 ins, so this was channels 1 and 2). When I switched to the mic on my webcam it worked perfectly. EDIT: Dev already fixed for multichannel audio inputs... I just hadn't dug through settings enough. For the free version nonetheless. Seriously incredible. Purchased pro version immediately after seeing this! |
Beta Was this translation helpful? Give feedback.
-
|
you should add a settings section to tweak num of cpus / threads weights etc. |
Beta Was this translation helpful? Give feedback.
-
|
Will ollama be supported as an alternative to openai and anthropic at one point ? |
Beta Was this translation helpful? Give feedback.
-
|
Hi, I've been using the new version of Macwhisper (Paid account) for a few weeks. Yesterday I went to launch it on my Macbook M2 and got a crash report. Here is a GTP summary: Any one run into this? Would appreciate any guidance. Thanks. From the crash report you provided, the key issue seems to be a segmentation fault (EXC_BAD_ACCESS) with SIGSEGV, which occurs when the program attempts to access memory that it shouldn't. In your case, it looks like the crash is happening in Thread 4, where a function in the MacWhisper app is attempting to read from an invalid address (far: 0x0000000000000004), which isn't mapped to any memory region. Key Indicators: Potential Causes:
Recommended Actions:
|
Beta Was this translation helpful? Give feedback.
-
|
mine is also crashing. Paid version. Mac M1 with 16gb of ram. I am reinstalling it and will see it that works. I wanted to batch about 150 files and I think that broke it... |
Beta Was this translation helpful? Give feedback.
-
|
Has anybody figured out any way to automate transcriptions with Mac Whisper? It appears to not have AppleScript or Shortcuts support, but I need to do weekly transcriptions and it would be great to be able to control Mac Whisper programatically so it can be part of an automatic workflow. |
Beta Was this translation helpful? Give feedback.
-
|
I came here to feature request CLI execution so I can call macwhisper from python or terminal. But Applescript would also work. I believe I could install whisper and torch but it seems a waste to double up model storage. |
Beta Was this translation helpful? Give feedback.
-
|
I absolutely love the dictation feature it is much better than the Apple dictation but at present the custom shortcut button doesn't work and I also noticed sometimes it makes a dictation noise but the microphone won't pop up and it does not work for instance right now so I have to use Apple dictation which is way less accurate. Any suggestions? |
Beta Was this translation helpful? Give feedback.
-
|
I absolutely love the app, and that it does the transcription fully offline. @jordibruin, thank you and to everyone who's contributed and help make this app happen. I get a lot of voice notes which are many times long, and end up feeding them through MacWhisper to transcribe. It would be nice to be able to control the translation feature... I've noticed however that with transcriptions that are bi-lingual (e.g. English-Arabic), some voice notes get transcribed without translation (i.e. English gets transcribed in English, and Arabic in Arabic), however in most cases MacWhisper will translate to one of the languages and only transcribe in that language. Is there any way to disable translation for a particular transcription, but keep the multi-language detections and transcriptions? Thanks! |
Beta Was this translation helpful? Give feedback.
-
|
@jordibruin seems not here but at X: https://x.com/jordibruin |
Beta Was this translation helpful? Give feedback.
This comment was marked as disruptive content.
This comment was marked as disruptive content.
-
|
@jordibruin it would be great a live transcription option |
Beta Was this translation helpful? Give feedback.
-
|
Maybe you could try Audio Note |
Beta Was this translation helpful? Give feedback.
-
|
@jordibruin I tried it but it cannot recognize the audio from audio interfaces like the |
Beta Was this translation helpful? Give feedback.
-
|
@jordibruin @mavericreal I'm assuming that your device has multiple channels. There is an option (even in the free version, I think) to flatten all channels into a single stream. I needed to enable that to get my audio interface (Behringer UMC404, an inexpensive 4-channel interface) working with this app. 
|
Beta Was this translation helpful? Give feedback.
-
|
Hey @alexgoodell, that worked. I'll give it another try. Thanks a lot for the tip! |
Beta Was this translation helpful? Give feedback.
-
|
Any plans to add wyoming server support? https://github.com/rhasspy/wyoming |
Beta Was this translation helpful? Give feedback.
-
|
There has got to be a better way to communicate with the developer. I love the app but can we move to someplace like github discussions even(edit: in its own separate repository)? I want to stay in touch about development but, no offense, don’t want to get a mail for every query |
Beta Was this translation helpful? Give feedback.
-
|
This is a Github discussion. |
Beta Was this translation helpful? Give feedback.
-
I meant not one on a completely different software repository . This is a whisper.cpp discussion. Not a macwhisper one This is a giant ass thread with all completely different topics |
Beta Was this translation helpful? Give feedback.
-
|
Yes, @jordibruin should really have his own Github repository for this software (even if it isn’t FOSS) given its clear popularity and the fact that people have issues. |
Beta Was this translation helpful? Give feedback.
-
|
The developer seems not to see this discussion. How about to ask the developer at X: https://x.com/jordibruin |
Beta Was this translation helpful? Give feedback.
-
|
Free open-source Mac app based on ggerganov work: |
Beta Was this translation helpful? Give feedback.
-
|
I'm looking for a live transcription |
Beta Was this translation helpful? Give feedback.
-
|
Do you have any idea why a podcast transcription would start in one language and then switch to the correct one (English, in my case)? Everything is fine after the first paragraph: Speaker 1 Speaker 2
Speaker 1 |
Beta Was this translation helpful? Give feedback.
-
|
Nice! there's also the open-source VoiceInk at https://github.com/Beingpax/VoiceInk |
Beta Was this translation helpful? Give feedback.
and others
-
First of all, a massive thanks to @ggerganov for making all this! Most of the low level stuff is voodoo to me, but I was able to get a native macOS app up and running thanks to all your hard work!
MacWhisper lets you run Whisper locally on your Mac without having to install anything else.
Features
MacWhisper is very basic right now, so please let me know if you run into anything. You can download it for free here:
http://goodsnooze.gumroad.com/l/macwhisper
Beta Was this translation helpful? Give feedback.
All reactions