DEV Community

#speechrecognition

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Local dictation on a 4 GB GPU: why one model beat Whisper + an LLM

Local dictation on a 4 GB GPU: why one model beat Whisper + an LLM

Comments
4 min read
NVIDIA's Open Transcription Model and Python Routing Middleware

NVIDIA's Open Transcription Model and Python Routing Middleware

Comments
4 min read
Turning 'vodka two point five' into a number: parsing spoken bar counts

Turning 'vodka two point five' into a number: parsing spoken bar counts

Comments
5 min read
Perch publishes three open releases for checking drug names in dictation

Perch publishes three open releases for checking drug names in dictation

Comments
3 min read
Speech-to-Text API 429 Rate Limits: 4 Candidate Evidence Safeguards

Speech-to-Text API 429 Rate Limits: 4 Candidate Evidence Safeguards

Comments
7 min read
Go Speech-to-Text API Rate Limits: 429 Retry-After Backoff and Queues

Go Speech-to-Text API Rate Limits: 429 Retry-After Backoff and Queues

Comments
8 min read
5 Speech-to-Text API Rate-Limit Checks — Node.js 429 Retry Queue Observability

5 Speech-to-Text API Rate-Limit Checks — Node.js 429 Retry Queue Observability

Comments
7 min read
How to Transcribe Phone Audio Using Your Computer in 2026

How to Transcribe Phone Audio Using Your Computer in 2026

Comments
5 min read
Whisper large-v3 hours of audio per dollar on four GPUs: RTX 5090, L40S, RTX A6000 and H100, five setups measured

Whisper large-v3 hours of audio per dollar on four GPUs: RTX 5090, L40S, RTX A6000 and H100, five setups measured

Comments
6 min read
Parakeet v3 vs Whisper vs Apple's on-device model in 25 languages, every transcript published

Parakeet v3 vs Whisper vs Apple's on-device model in 25 languages, every transcript published

1
Comments 2
3 min read
Should You Build or Buy AI Meeting Transcription for Your Product?

Should You Build or Buy AI Meeting Transcription for Your Product?

1
Comments
6 min read
I built an open-source voice input for macOS that never uploads your voice

I built an open-source voice input for macOS that never uploads your voice

1
Comments 2
3 min read
Parakeet Redux: is a 178 MB speech model useful in the real world?

Parakeet Redux: is a 178 MB speech model useful in the real world?

1
Comments
16 min read
Your ASR confidence score is a number you can act on. We were throwing it away.

Your ASR confidence score is a number you can act on. We were throwing it away.

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