It's not transcribing the audios

Please. I need tô transcriber

The app stopped working. It's not transcribing the audios

A Getting Started Guide or a Tests tutorial is needed for the community to start work in the project. I just got the news that the TranscriberBot is open-source, but I don't know where to start. I think there should be a guide to help install and run the project and test the code.

Off course, someone who knows about python projects can get it running, but a guide is helpful for the newcomers.

I've sent an audio in private and also in a group and TranscriberBot answered: "Não pude transcrever o áudio" (transcription_failed string in pt_BR).

When I select to transcribe from catalan (ca-ES) the bot tries to transcribe from english

Sorry to bother you sir
But the bot stopped working
Im so so sorry but I'm depending on it to sutdy for the finals

Buongiorno, il bot non fa nessuna funzione su telegram, ha funzionato 1 sola volta e poi si è bloccato, come devo fare?

Unless I keep retrying more then two times!
And sometimes: could not transcribe
What are the best practices with this bot?
Is there a special preferred audio long and quality?
To ensure the complete transcribing for the first time?
Thanks

I had this idea during this use case:

1. I needed to transcribe an 1-hour long interview in Brazilian Portuguese (the file was 80MB+ and was in M4A format)
2. I split the original file in 5 OGG parts using ffmpeg (~8MB each part)
3. I sent the files to the bot, received lots of 4k-chars messages in reply and copied to a text editor (this was boring)
4. I found some errors when reading the text in the editor, but it was hard to find the error chunk in the audio file (so I could listen and fix it manually)

Being able to download the transcription in a text file will solve problem in item 3. Using a subtitle file format (like srt) would help a lot in item 4. The behavior of attaching the file could be triggered automatically for files longer than 1 minute.

I'm willing to implement this feature if the maintainers accept the proposal.

The bot all commands in group chats from anonymous admins. To fix this behavior probably need to change FilterIsAdmin so it also checks if message was sent as the group itself (messages sent by anonymous admins show up as if the group sent the message, like it happens on channels).

I tried to use it in English and Italian, but it can't transcribe anything anymore. It just continue to fail again and again

Trascriber is offline

Hi, the bot is currently down, it won't reply to commands and it doesn't transcribe the audio files

Sorry,
But the bot stopped working
Im so so sorry but I'm depending on it to sutdy for the finals

Have feature to ignore some users of channel. This will avoid translate other bots.

Hi. It's not transcribing the audios

I found that the development branch is behind master for some commits but also it has a new merge (PR #24) which hasn't been merged into master yet.
Are you going to merge it on master and deploy this new version (supports video files)?

There's no instrucctions or guidelines for contributing. Is the repository open to contributions?

The most use case for me is to record a voice clip, wait for transcription, copy the whole answer and then paste it in another place (I usually do this using a cellphone). I imagine this is the most use case in general for private chats.
Since I don't want to paste the "Text: " part of the message and it's hard to copy only a portion of the text in cellphones, I suggest removing these prefixes (strings transcription_text and ocr_result) in private chats. It's already clear that the answer is the transcribed text for that audio since it's an reply to the sent audio clip and well, the bot name is TranscriberBot! :)
What do you think?

the app is not working

Figure 1. Result from bot after sending an image with /enable_photos enabled.

I have been trying to transcribe images whilst and within groups, for ease of access to blind members (they can use an app to read screen, but many of them can't read telegram images). The bot gets stuck at "Recognizing" for several minutes (in fact, days so far).

I thought that was some misconfiguration so, I have tried to upload a random image directly to bot and see if works. Sadly, it doesn't work too. Not sure if its a problem of certain images or it doesn't work anymore. Uploaded a sample image if you want to test or need some input on "failed" cases.

Figure 2. Sample image provided for recognition.

Don't get me wrong. Your bot is great and really helps transcribing audio. Great work!

Thanks in advance and hope to see this working again.

I'd like to report a possible bug when a file is pretty long and text length is longer than the maximum allowed number of a single message. The bot sends only one message in this case and skips the rest.

This can be easily reproduced by sending any long file (20 minutes for example).

Hi,

The bot has been quite buggy. The vast majority of times, if an audio is long, it won't transcribe it all. It will only do a portion, and even the portion percentage may differ here and there. Sometimes it does 20%, another time 40%, never 100%

I was transcribing from Arabic (if that helps)

Any idea? Is there anything I can do for it to do it all? And if it's a bot issue then maybe it can be looked into

Has been saying "hello portal" on several different en-us transcripts.