• bartleeanderson 30 minutes ago

    Very cool. I was reading through the various threads here. I am working on adding stt and tts to an AI DungeonMaster. Just a personal fun project, am working on the adventure part of it now. This will come in handy. I had dungeon navigation via commands working but started over and left it at the point where I am ready to merge the navigation back in again once I was happy with a slimmer version with one file. It will be fun to be able to talk to the DM and have it respond with voice and actions. The diarization will be very helpful if I can create a stream where it can hear all of us conversing at once. But baby steps. Still working on getting the whole campaign working after I get characters created and put in a party :)

    • mijoharas 4 hours ago

      Ok, cool! I was actually one of the people on the hyprnote HN thread asking for a headless mode!

      I was actually integrating some whisper tools yesterday. I was wondering if there was a way to get a streaming response, and was thinking it'd be nice if you can.

      I'm on linux, so don't think I can test out owhisper right now, but is that a thing that's possible?

      Also, it looks like the `owhisper run` command gives it's output as a tui. Is there an option for a plain text response so that we can just pipe it to other programs? (maybe just `kill`/`CTRL+C` to stop the recording and finalize the words).

      Same question for streaming, is there a way to get a streaming text output from owhisper? (it looks like you said you create a deepgram compatible api, I had a quick look at the api docs, but I don't know how easy it is to hook into it and get some nice streaming text while speaking).

      Oh yeah, and diarisation (available with a flag?) would be awesome, one of the things that's missing from most of the easiest to run things I can find.

    • clickety_clack 4 hours ago

      Please find a way to add speaker diarization, with a way to remember the speakers. You can do it with pyannote, and get a vector embedding of each speaker that can be compared between audio samples, but that’s a year old now so I’m sure there’s better options now!

      • yujonglee 4 hours ago

        yeah that is on the roadmap!

      • wanderingmind an hour ago

        Thank you for taking the time to build something and share it. However what is the advantage of using this over whisper.cpp stream that can also do real time conversion?

        https://github.com/ggml-org/whisper.cpp/tree/master/examples...

        • yujonglee 20 minutes ago

          Its lot more than that.

          - It supports other models like moonshine.

          - It also works as proxy for cloud model providers.

          - It can expose local models as Deepgram compatible api server

        • solarkraft 4 hours ago

          Wait, this is cool.

          I just spent last week researching the options (especially for my M1!) and was left wishing for a standard, full-service (live) transcription server for Whisper like OLlama has been for LLMs.

          I’m excited to try this out and see your API (there seems to be a standard vaccuum here due to openai not having a real time transcription service, which I find to be a bummer)!

          Edit: They seem to emulate the Deepgram API (https://developers.deepgram.com/reference/speech-to-text-api...), which seems like a solid choice. I’d definitely like to see a standard emerging here.

        • elektor an hour ago

          Cool tool! Are you guys releasing Hyprnote for Windows this month?

          • yujonglee 22 minutes ago

            probably end of this month or early next month. not 100% sure.

          • JP_Watts 5 hours ago

            I’d like to use this to transcribe meeting minutes with multiple people. How could this program work for that use case?

            • yujonglee 5 hours ago

              If your use-case is meeting, https://github.com/fastrepl/hyprnote is for you. OWhisper is more like a headless version of it.

              • JP_Watts 4 hours ago

                Can you describe how it pick different voices? Does it need separate audio channels, or does it recognize different voices on the same audio input?

                • yujonglee 4 hours ago

                  It separate mic/speaker as 2 channel. So you can reliably get "what you said" vs "what you heard".

                  For splitting speaker within channel, we need AI model to do that. It is not implemented yet, but I think we'll be in good shape somewhere in September.

                  Also we have transcript editor that you can easily split segment, assign speakers.

              • sxp 4 hours ago

                If you want to transcribe meeting notes, whisper isn't the best tool because it doesn't separate the transcribe by speakers. There are some other tools that do that, but I'm not sure what the best local option is. I've used Google's cloud STT with the diarization option and manually renamed "Speaker N" after the fact.

              • yujonglee 5 hours ago

                Happy to answer any questions!

                These are list of local models it supports:

                - whisper-cpp-base-q8

                - whisper-cpp-base-q8-en

                - whisper-cpp-tiny-q8

                - whisper-cpp-tiny-q8-en

                - whisper-cpp-small-q8

                - whisper-cpp-small-q8-en

                - whisper-cpp-large-turbo-q8

                - moonshine-onnx-tiny

                - moonshine-onnx-tiny-q4

                - moonshine-onnx-tiny-q8

                - moonshine-onnx-base

                - moonshine-onnx-base-q4

                - moonshine-onnx-base-q8

                • shekhar101 an hour ago

                  FYI: owhisper pull whisper-cpp-large-turbo-q8 Failed to download model.ggml: Other error: Server does not support range requests. Got status: 200 OK

                  But the base-q8 works (and works quite well!). The TUI is really nice. Speaker diarization would make it almost perfect for me. Thanks for building this.

                  • yujonglee 22 minutes ago

                    we store data in R2 and range query sometime glitch... It might work if you retry it

                  • alkh 3 hours ago

                    Sorry, maybe I missed it but I didn't see this list on your website. I think it is a good idea to add this info there. Besides that, thank you for the effort and your work! I will definetely give it a try

                    • yujonglee 3 hours ago

                      got it. fyi if you run `owhisper pull --help`, this info is printed

                    • phkahler 4 hours ago

                      I thought whisper and others took large chunks (20-30 seconds) of speech, or a complete wave file as input. How do you get real-time transcription? What size chunks do you feed it?

                      To me, STT should take a continuous audio stream and output a continuous text stream.

                      • yujonglee 4 hours ago

                        I use VAD to chunk audio.

                        Whisper and Moonshine both works in a chunk, but for moonshine:

                        > Moonshine's compute requirements scale with the length of input audio. This means that shorter input audio is processed faster, unlike existing Whisper models that process everything as 30-second chunks. To give you an idea of the benefits: Moonshine processes 10-second audio segments 5x faster than Whisper while maintaining the same (or better!) WER.

                        Also for kyutai, we can input continuous audio in and get continuous text out.

                        - https://github.com/moonshine-ai/moonshine - https://docs.hyprnote.com/owhisper/configuration/providers/k...

                        • mijoharas 4 hours ago

                          Something like that, in a cli tool, that just gives text to stdout would be perfect for a lot of use cases for me!

                          (maybe with an `owhisper serve` somewhere else to start the model running or whatever.)

                          • yujonglee 4 hours ago

                            Are you thinking about the realtime use-case or batch use-case?

                            For just transcribing file/audio,

                            `owhisper run <MODEL> --file a.wav` or

                            `curl httpsL//something.com/audio.wav | owhisper run <MODEL>`

                            might makes sense.

                            • mijoharas 3 hours ago

                              agreed, both of those make sense, but I was thinking realtime. (pipes can stream data, I'd like and find useful something that can stream tts to stdout in realtime.)

                  • DiabloD3 3 hours ago

                    I suggest you don't brand this "Ollama for X". They've become a commercial operation that is trying to FOSS-wash their actions through using llama.cpp's code and then throwing their users under the bus when they can't support them.

                    I see that you are also using llama.cpp's code? That's cool, but make sure you become a member of that community, not an abuser.

                    • yujonglee 3 hours ago

                      yeah we use whisper.cpp for whisper inference. this is more like a community-focused project, not a commercial product!