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

Show HN: Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3

github.com

Post reply on HN
Print view View original

81–90 of 92 posts

Re: Show HN: Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3

#81

Post by fittingopposite »

agentifysh wrote: post #80
fittingopposite wrote: post #70

Earlier quoted context omitted.

Also running parakeet on my phone with https://github.com/notune/android_transcribe_app Very lightweight and good quality

This is actually pretty impressive. What kinda phone are you using? Are you noticing any drain on battery heat?Do you think it's possible to get this working with Flutter on iOS?

2-3 years old Android flagship phone with 8 GB RAM. When I looked for an app for parakeet, I think I also came across iOS apps. Don't recall it since I use Android. Seems light on the phone/battery. Don't observe any drain but I also only record shorter transcripts at once. Side note: Parakeet is actually pretty nice to do meetings with oneself. Did that on a computer while driving for an hour (split in several transcript chunks). Processed the raw meeting notes afterwards with an LLM. Effective use of the time in the car...

Re: Show HN: Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3

#82

Post by agentifysh »

fittingopposite wrote: post #81
agentifysh wrote: post #80

Earlier quoted context omitted.

This is actually pretty impressive. What kinda phone are you using? Are you noticing any drain on battery heat?Do you think it's possible to get this working with Flutter on iOS?

2-3 years old Android flagship phone with 8 GB RAM. When I looked for an app for parakeet, I think I also came across iOS apps. Don't recall it since I use Android. Seems light on the phone/battery. Don't observe any drain but I also only record shorter transcripts at once. Side note: Parakeet is actually pretty nice to do meetings with oneself. Did that on a computer while driving for an hour (split in several trans…

Thank you for sharing ! What about the quality of the transcripts? Is it able to do live streaming?

Re: Show HN: Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3

#83

Post by fittingopposite »

agentifysh wrote: post #82
fittingopposite wrote: post #81

Earlier quoted context omitted.

2-3 years old Android flagship phone with 8 GB RAM. When I looked for an app for parakeet, I think I also came across iOS apps. Don't recall it since I use Android. Seems light on the phone/battery. Don't observe any drain but I also only record shorter transcripts at once. Side note: Parakeet is actually pretty nice to do meetings with oneself. Did that on a computer while driving for an hour (split in several trans…

Thank you for sharing ! What about the quality of the transcripts? Is it able to do live streaming?

Unfortunately, Parakeet doesn't support streaming like Moonshot does (as much as I know). Would be perfect to have sth of the size of Parakeet but supporting streaming. Still hope Nvidia releases a V4 with that feature :) Otherwise, I think STT is basically a solved problem running locally on edge devices.

Re: Show HN: Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3

#84

Post by Leftium »

Try Moonshine with a browser GUI:

    uv tool install rift-local && rift-local serve --open
This opens RIFT[1], my web frontend for local transcription with a copy button. You can also compare against Web Speech API and other models (including cloud API's).

https://github.com/Leftium/rift-local

[1]: https://rift-transcription.vercel.app/local-setup

Re: Show HN: Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3

#85

Post by mattmcegg »

francislavoie wrote: post #21

I've helped many Twitch streamers set up https://github.com/royshil/obs-localvocal to plug transcription & translation into their streams, mainly for German audio to English subtitles. I'd love a faster and more accurate option than Whisper, but streamers need something off-the-shelf they can install in their pipeline, like an OBS plugin which can just grab the audio from their OBS audio sources. I see a couple obvio…

I released a OBS plugin (and optional RTMP relay) that does exactly this. It can do real time translated captions and voice cloning/dubbing. The plugin lets you choose an audio source, then creates each language's captions and dub as new Sources. Use them however you'd like! check it out! https://streamfluent.ai

Re: Show HN: Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3

#86

Post by Leftium »

T0mSIlver wrote: post #59

Congrats on the results. The streaming aspect is what I find most exciting here. I built a macOS dictation app ( https://github.com/T0mSIlver/localvoxtral ) on top of Voxtral Realtime, and the UX difference between streaming and offline STT is night and day. Words appearing while you're still talking completely changes the feedback loop. You catch errors in real time, you can adjust what you're saying mid-sentence, a…

My app uses this moonshine-voice python package, so you can experience it yourself here: https://rift-transcription.vercel.app/local-setup

I made moonshine the default because it has the best accuracy/latency (aside from Web Speech API, but that is not fully local)

I plan to add objective benchmarks in the future, so multiple models can be compared against the same audio data...

---

I made a custom WebSocket server for my project. It defines its own API (modeled on the Sherpa-onnx API), but you could adjust it to output the OpenAI Realtime API: https://github.com/Leftium/rift-local

(note rift-local is optimized for single connections, or rather not optimized to handle multiple WS connections)

Re: Show HN: Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3

#87

Post by Leftium »

fittingopposite wrote: post #83
agentifysh wrote: post #82

Earlier quoted context omitted.

Thank you for sharing ! What about the quality of the transcripts? Is it able to do live streaming?

Unfortunately, Parakeet doesn't support streaming like Moonshot does (as much as I know). Would be perfect to have sth of the size of Parakeet but supporting streaming. Still hope Nvidia releases a V4 with that feature :) Otherwise, I think STT is basically a solved problem running locally on edge devices.

I think there is a streaming version of Parakeet. It is often referred to as Nemotron, though.

I tried comparing Parakeet streaming with Moonshine streaming. Moonshine is smaller, and I felt it was subjectively faster with about the same level of accuracy.

Re: Show HN: Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3

#88

Post by Leftium »

syntaxing wrote: post #23
Karrot_Kream wrote: post #12

According to the OpenASR Leaderboard [1], looks like Parakeet V2/V3 and Canary-Qwen (a Qwen finetune) handily beat Moonshine. All 3 models are open, but Parakeet is the smallest of the 3. I use Parakeet V3 with Handy and it works great locally for me. [1]: https://huggingface.co/spaces/hf-audio/open_asr_leaderboard

How much VRAM does parakeet take for you? For some reason it takes 4GB+ for me using the onyx version even though it’s 600M parameters

There are different versions of the parakeet model. The 8-bit quantized version doesn't use as many bits. Thus it saves space (only using about 600MB) while maintaining about the same level of accuracy.

I think most apps that use Parakeet tend to use this version of the model?

See if Parakeet (Nemotron) still uses 4GB+ with my implementation: https://rift-transcription.vercel.app/local-setup

Re: Show HN: Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3

#89

Post by Leftium »

nmstoker wrote: post #14

Any plans regarding JavaScript support in the browser? There was an issue with a demo but it's missing now. I can't recall for sure but I think I got it working locally myself too but then found it broke unexpectedly and I didn't manage to find out why.

WASM-based port: https://github.com/moonshine-ai/moonshine-js

I also did a survey of other in-browser transcription solutions: https://github.com/Leftium/rift-transcription/blob/main/refe...

- Notably, there is an (unrelated?) moonshine demo based on transformers.js (using WebGPU) with WASM fallback.

Post reply on HN