LowEndBoxTV: OpenAI Whisper? No! There Are Better Options

Looking for a transcription solution? Sure, you can pay one of the big cloud services but that isn't the LowEnd way! Let's see what Piotr's got for us.

LowEndBox
Release v0.9.0 · jkawamoto/ctranslate2-rs

Add support for the Whisper model. See also example code.

GitHub

ついでにCLI翻訳ツールも作った

https://github.com/jkawamoto/vsop

#rust #CTranslate2 #llm #fugumt

GitHub - jkawamoto/vsop: Command line translation tool using CTranslate2

Command line translation tool using CTranslate2. Contribute to jkawamoto/vsop development by creating an account on GitHub.

GitHub

NLLBの精度がイマイチだったので放置していたCTranslate2のRustバインディングだけれど、FuguMTが良かったので手直ししていました

https://github.com/jkawamoto/ctranslate2-rs

#rust #CTranslate2 #llm #fugumt

GitHub - jkawamoto/ctranslate2-rs: Rust bindings for OpenNMT/CTranslate2

Rust bindings for OpenNMT/CTranslate2. Contribute to jkawamoto/ctranslate2-rs development by creating an account on GitHub.

GitHub

他になさそうだったので、FuguMTをCTranslate2用に変換したものを作成しました

https://huggingface.co/jkawamoto/fugumt-en-ja-ct2

#ctranslate2 #fugumt #llm

jkawamoto/fugumt-en-ja-ct2 · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

One of the best things coming out the current AI-boom is automatic subtitle transcribing.

I am currently using faster-whisper[0] with the small ASR_MODEL using CPU only and it takes my low-powered i5-6500T only 10 minutes to transcribe 46 minutes.

The subtitles are 10x better than what you get out of Youtubes automatic subtitles and those are usually good enough for me to get a feel for what is happening.

[0]: https://github.com/SYSTRAN/faster-whisper

#ai #whisper #OpenAI #CTranslate2 #subtitles

GitHub - SYSTRAN/faster-whisper: Faster Whisper transcription with CTranslate2

Faster Whisper transcription with CTranslate2. Contribute to SYSTRAN/faster-whisper development by creating an account on GitHub.

GitHub
FastAPIを使ってストリーム対応のLLM API RESTサーバを作る on Databricks - Qiita

Databricksを使って動作確認しています。一部、Databricks固有の処理が含まれます。導入下記の前回記事では、langchain + CTranslate2を使ってストリーミングする…

Qiita