faster-whisper
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
4recommend
0warn against
Jan 9, 2026first mention
Oct 7, 2026latest mention
Why people recommend it
“faster-whisper produces the text then onnx scores all my HA entities”
Show 2 more
“Thanks to faster-whisper and local models using quantization, I use it in all places”
“it completes in a fraction of the time using batching”
Caveats and dissent
No one in these comments warned against it.
Threads where it came up
- Jev-Driven SRE Diagnosis: What Worked and What Failed 1 mention
- Transcribe.cpp 1 mention
- Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor 1 mention
- I Fired Google 1 mention
- Show HN: Free Alternative to Wispr Flow, Superwhisper, and Monologue 1 mention
- Dell's CES 2026 chat was the most pleasingly un-AI briefing I've had in 5 years 1 mention
Data: faster-whisper.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 6
“faster-whisper produces the text then onnx scores all my HA entities”
“I'm really happy with faster-whisper on a GPU.”
“I use Systran/faster-whisper-medium for real-time subtitling”
“Voice input is openWakeWord for the wake word plus faster-whisper for speech-to-text, all on-device.”
“Thanks to faster-whisper and local models using quantization, I use it in all places”
“it completes in a fraction of the time using batching”