From 9bb6623cfb6f48491ff1f860c65246704419ec4c Mon Sep 17 00:00:00 2001 From: cck0517 Date: Thu, 16 Nov 2023 16:05:26 -0800 Subject: [PATCH 1/5] added description --- README.md | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 24a6f8f..54ead4b 100644 --- a/README.md +++ b/README.md @@ -11,8 +11,14 @@ into `.lrc` files in the desired language using [OpenAI-GPT](https://github.com/ ## Installation -1. Please install CUDA and cuDNN first according to https://opennmt.net/CTranslate2/installation.html to - enable `faster-whisper`. +1. Please install CUDA 11.x and [cuDNN 8 for CUDA 11](https://developer.nvidia.com/cudnn) first according to https://opennmt.net/CTranslate2/installation.html to + enable `faster-whisper`. + Currently `faster-whisper` is only compatible with CUDA version 11 (11.x). + `faster-whisper` also needs * [cuBLAS for CUDA 11](https://developer.nvidia.com/cublas) installed. + (For Windows Users only) Windows user can Download the libraries from Purfview's repository: + Purfview's [whisper-standalone-win](https://github.com/Purfview/whisper-standalone-win) provides the required NVIDIA libraries for Windows in a [single archive](https://github.com/Purfview/whisper-standalone-win/releases/tag/libs). Decompress the archive and place the libraries in a directory included in the `PATH`. + + 2. Add your [OpenAI API key](https://platform.openai.com/account/api-keys) to environment variable `OPENAI_API_KEY`. From 134e7d76ce719f8a925a483c16c8c4e284513609 Mon Sep 17 00:00:00 2001 From: cck0517 Date: Thu, 16 Nov 2023 16:07:44 -0800 Subject: [PATCH 2/5] shortened sentences --- README.md | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 54ead4b..783824f 100644 --- a/README.md +++ b/README.md @@ -11,10 +11,9 @@ into `.lrc` files in the desired language using [OpenAI-GPT](https://github.com/ ## Installation -1. Please install CUDA 11.x and [cuDNN 8 for CUDA 11](https://developer.nvidia.com/cudnn) first according to https://opennmt.net/CTranslate2/installation.html to - enable `faster-whisper`. - Currently `faster-whisper` is only compatible with CUDA version 11 (11.x). +1. Please install CUDA 11.x and [cuDNN 8 for CUDA 11](https://developer.nvidia.com/cudnn) first according to https://opennmt.net/CTranslate2/installation.html to enable `faster-whisper`. `faster-whisper` also needs * [cuBLAS for CUDA 11](https://developer.nvidia.com/cublas) installed. + (For Windows Users only) Windows user can Download the libraries from Purfview's repository: Purfview's [whisper-standalone-win](https://github.com/Purfview/whisper-standalone-win) provides the required NVIDIA libraries for Windows in a [single archive](https://github.com/Purfview/whisper-standalone-win/releases/tag/libs). Decompress the archive and place the libraries in a directory included in the `PATH`. From 79164cddf0418c1833ea8c5d74d1925b65b6c4bb Mon Sep 17 00:00:00 2001 From: cck0517 Date: Thu, 16 Nov 2023 16:09:33 -0800 Subject: [PATCH 3/5] added space --- README.md | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 783824f..ab01b29 100644 --- a/README.md +++ b/README.md @@ -11,10 +11,12 @@ into `.lrc` files in the desired language using [OpenAI-GPT](https://github.com/ ## Installation -1. Please install CUDA 11.x and [cuDNN 8 for CUDA 11](https://developer.nvidia.com/cudnn) first according to https://opennmt.net/CTranslate2/installation.html to enable `faster-whisper`. - `faster-whisper` also needs * [cuBLAS for CUDA 11](https://developer.nvidia.com/cublas) installed. +1. Please install CUDA 11.x and [cuDNN 8 for CUDA 11](https://developer.nvidia.com/cudnn) first according to https://opennmt.net/CTranslate2/installation.html to enable `faster-whisper`. + + `faster-whisper` also needs * [cuBLAS for CUDA 11](https://developer.nvidia.com/cublas) installed. (For Windows Users only) Windows user can Download the libraries from Purfview's repository: + Purfview's [whisper-standalone-win](https://github.com/Purfview/whisper-standalone-win) provides the required NVIDIA libraries for Windows in a [single archive](https://github.com/Purfview/whisper-standalone-win/releases/tag/libs). Decompress the archive and place the libraries in a directory included in the `PATH`. From 1b6f707afc947058741da4c2d575bedb357c14ed Mon Sep 17 00:00:00 2001 From: cck0517 Date: Thu, 16 Nov 2023 16:12:28 -0800 Subject: [PATCH 4/5] fixed spacing issues --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index ab01b29..b595fa7 100644 --- a/README.md +++ b/README.md @@ -13,10 +13,10 @@ into `.lrc` files in the desired language using [OpenAI-GPT](https://github.com/ 1. Please install CUDA 11.x and [cuDNN 8 for CUDA 11](https://developer.nvidia.com/cudnn) first according to https://opennmt.net/CTranslate2/installation.html to enable `faster-whisper`. - `faster-whisper` also needs * [cuBLAS for CUDA 11](https://developer.nvidia.com/cublas) installed. + `faster-whisper` also needs [cuBLAS for CUDA 11](https://developer.nvidia.com/cublas) installed. (For Windows Users only) Windows user can Download the libraries from Purfview's repository: - + Purfview's [whisper-standalone-win](https://github.com/Purfview/whisper-standalone-win) provides the required NVIDIA libraries for Windows in a [single archive](https://github.com/Purfview/whisper-standalone-win/releases/tag/libs). Decompress the archive and place the libraries in a directory included in the `PATH`. From 62f2f5215a65d862b60a62c35a87c563a071000d Mon Sep 17 00:00:00 2001 From: cck0517 Date: Thu, 16 Nov 2023 16:15:10 -0800 Subject: [PATCH 5/5] added expand section to improve readability --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index b595fa7..6206396 100644 --- a/README.md +++ b/README.md @@ -14,11 +14,15 @@ into `.lrc` files in the desired language using [OpenAI-GPT](https://github.com/ 1. Please install CUDA 11.x and [cuDNN 8 for CUDA 11](https://developer.nvidia.com/cudnn) first according to https://opennmt.net/CTranslate2/installation.html to enable `faster-whisper`. `faster-whisper` also needs [cuBLAS for CUDA 11](https://developer.nvidia.com/cublas) installed. +
+ For Windows Users (click to expand) (For Windows Users only) Windows user can Download the libraries from Purfview's repository: Purfview's [whisper-standalone-win](https://github.com/Purfview/whisper-standalone-win) provides the required NVIDIA libraries for Windows in a [single archive](https://github.com/Purfview/whisper-standalone-win/releases/tag/libs). Decompress the archive and place the libraries in a directory included in the `PATH`. +
+ 2. Add your [OpenAI API key](https://platform.openai.com/account/api-keys) to environment variable `OPENAI_API_KEY`.