DEV Community

Whisper

Whisper is a versatile speech recognition model that can transcribe, identify, and translate multiple languages.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Code for preventing hallucinations only failed during hallucinations

Code for preventing hallucinations only failed during hallucinations

Comments
11 min read
Where Did the AI Learn to Elongate Its "Konnichiwa"?

Where Did the AI Learn to Elongate Its "Konnichiwa"?

Comments
7 min read
Feed audio to Whisper in Rust without ever shelling out to ffmpeg

Feed audio to Whisper in Rust without ever shelling out to ffmpeg

Comments
8 min read
Practical Techniques to Improve Faster-Whisper Recognition Accuracy — Use Recent Conversations, Not Dictionaries, for initial_prompt

Practical Techniques to Improve Faster-Whisper Recognition Accuracy — Use Recent Conversations, Not Dictionaries, for initial_prompt

2
Comments
4 min read
My First GitHub Project: From A Local Folder To GitHub Using Git And SSH

My First GitHub Project: From A Local Folder To GitHub Using Git And SSH

1
Comments 1
3 min read
Building Li Translate: An Open-Source AI Subtitle Generator with Natural AI Translation 🚀

Building Li Translate: An Open-Source AI Subtitle Generator with Natural AI Translation 🚀

Comments 1
2 min read
what is the best offline voice to text software?

what is the best offline voice to text software?

Comments
3 min read
Streaming ASR vs Whisper on mobile: when to switch

Streaming ASR vs Whisper on mobile: when to switch

8
Comments 2
9 min read
Building Private Voice Notes for iOS and Android Without the Cloud

Building Private Voice Notes for iOS and Android Without the Cloud

8
Comments
12 min read
The Culprit Behind the 'Slow Speech' Bug in Voice Conversion Was Whisper's 30-Second Limit

The Culprit Behind the 'Slow Speech' Bug in Voice Conversion Was Whisper's 30-Second Limit

Comments
5 min read
Apple SpeechAnalyzer vs whisper.cpp: A 40-Speaker Mac Benchmark

Apple SpeechAnalyzer vs whisper.cpp: A 40-Speaker Mac Benchmark

Comments
5 min read
Why Privacy Became the Reason We Built PolyTalk

Why Privacy Became the Reason We Built PolyTalk

1
Comments
3 min read
The eye corrects the ear: fixing my LLM's video hallucinations with OCR and a VAD gate

The eye corrects the ear: fixing my LLM's video hallucinations with OCR and a VAD gate

Comments 4
2 min read
Speech-to-Text API Comparison: Whisper API Options in 2026

Speech-to-Text API Comparison: Whisper API Options in 2026

1
Comments
7 min read
Free Video subtitles in seconds — no signup, no watermark, no upload

Free Video subtitles in seconds — no signup, no watermark, no upload

Comments
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.