Find similar content

Source channel @githubtrending · Post #15385 · Jan 2

#python#deep_learning#inference#openai#quantization#speech_recognition#speech_to_text#transformer#whisper Faster-Whisper is a fast version of OpenAI's Whisper that transcribes audio up to 4x quicker with the same accuracy, using less memory on CPU or GPU—benchmarks show it beats original Whisper (e.g., 1m03s vs 2m23s for 13-min audio on GPU). Install via `pip install faster-whisper`, no FFmpeg needed, and use simple Python code like `WhisperModel("large-v3").transcribe("audio.mp3")` for segments with timestamps. You benefit by getting quick, efficient speech-to-text for real-time apps, saving time and resources on long files or batches. https://github.com/SYSTRAN/faster-whisper

Hashtags

#python #deep_learning #inference #openai #quantization #speech_recognition #speech_to_text #transformer #whisper

Results

2 similar posts found

Search: #hetzner

当前筛选 #hetzner清除筛选

VPS简测

@vps_test · Post #205 · 06/20/2023, 02:13 PM

Find similar View

JJNEWS Hetzner将要全面弃用Intel的机器 Hetzner is going to remove dedicated Intel vCPU plans! Servers with dedicated Intel® vCPUs are deprecated Starting on 18 July 2023, all server plans with Intel® vCPUs (CCX11, CCX21, CCX31, CCX41, CCX51) will no longer be available for order. Existing servers are not affected by this deprecation and they 配备专用英特尔®vCPU的服务器已弃用从2023年7月18日开始，所有配备英特尔®vCPU的服务器计划(CCX11、CCX21、CCX31、CCX41、CCX51)将不再可供订购。现有服务器不受此弃用的影响，它们将继续工作。如果您想要将配备英特尔®vCPU的现有服务器迁移到服务器计划 #jjnews#hetzner

Hashtags

#jjnews #hetzner

Host Testing and evaluation

@HostEvaluate · Post #784 · 06/03/2022, 07:06 PM

Find similar View

#FI#Hetzner HostProvider: Hetzner Location: Helsinki, Finland Specification: 2vCore (AMD EPYC) | 2GB RAM | 40GB SSD | 20T @ 1Gbps | € 4.75 / Month Looking glass: hel.icmp.hetzner.com https://paste.red/p/d7d8ed1c86ee Hetzner 赫尔辛基公有云 VPS, 性能不错。

Hashtags

#fi #hetzner