From: Petter Reinholdtsen Date: Sun, 23 Apr 2023 07:55:00 +0000 (+0200) Subject: Generated. X-Git-Url: http://pere.pagekite.me/gitweb/homepage.git/commitdiff_plain/ca102ed31c7579201357f4311c16d8b833184f7d?ds=inline;hp=571d502da7ec89e406026df339bd1bd012b4e126 Generated. --- diff --git a/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html b/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html index d8e03289cf..564de4cff4 100644 --- a/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html +++ b/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html @@ -22,7 +22,7 @@
Speech to text, she APTly whispered, how hard can it be?
23rd April 2023
-

While visiting a convention during Eastern, it occurred to me that +

While visiting a convention during Easter, it occurred to me that it would be great if I could have a digital Dictaphone with transcribing capabilities, providing me with texts to cut-n-paste into stuff I need to write. The background is that long drives often bring @@ -35,11 +35,11 @@ audio files and provide text representation of the speech in that audio recording. It handle multiple languages and according to its creators even can translate into a different language than the spoken one. I have not tested the latter feature. It can either use the CPU -or a GPU with CODA support. As far as I can tell, CODA in practice +or a GPU with CUDA support. As far as I can tell, CUDA in practice limit that feature to NVidia graphics cards. I have few of those, as they do not work great with free software drivers, and have not tested the GPU option. While looking into the matter, I did discover some -work to provide CODA support on non-NVidia GPUs, and some work with +work to provide CUDA support on non-NVidia GPUs, and some work with the library used by Whisper to port it to other GPUs, but have not spent much time looking into GPU support yet. I've so far used an old X220 laptop as my test machine, and only transcribed using its diff --git a/blog/archive/2023/04/04.rss b/blog/archive/2023/04/04.rss index 616c07e281..90dd579aae 100644 --- a/blog/archive/2023/04/04.rss +++ b/blog/archive/2023/04/04.rss @@ -11,7 +11,7 @@ https://people.skolelinux.org/pere/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html https://people.skolelinux.org/pere/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html Sun, 23 Apr 2023 09:40:00 +0200 - <p>While visiting a convention during Eastern, it occurred to me that + <p>While visiting a convention during Easter, it occurred to me that it would be great if I could have a digital Dictaphone with transcribing capabilities, providing me with texts to cut-n-paste into stuff I need to write. The background is that long drives often bring @@ -24,11 +24,11 @@ audio files and provide text representation of the speech in that audio recording. It handle multiple languages and according to its creators even can translate into a different language than the spoken one. I have not tested the latter feature. It can either use the CPU -or a GPU with CODA support. As far as I can tell, CODA in practice +or a GPU with CUDA support. As far as I can tell, CUDA in practice limit that feature to NVidia graphics cards. I have few of those, as they do not work great with free software drivers, and have not tested the GPU option. While looking into the matter, I did discover some -work to provide CODA support on non-NVidia GPUs, and some work with +work to provide CUDA support on non-NVidia GPUs, and some work with the library used by Whisper to port it to other GPUs, but have not spent much time looking into GPU support yet. I've so far used an old X220 laptop as my test machine, and only transcribed using its diff --git a/blog/archive/2023/04/index.html b/blog/archive/2023/04/index.html index eb52e47a8e..acfe71934a 100644 --- a/blog/archive/2023/04/index.html +++ b/blog/archive/2023/04/index.html @@ -29,7 +29,7 @@ 23rd April 2023

-

While visiting a convention during Eastern, it occurred to me that +

While visiting a convention during Easter, it occurred to me that it would be great if I could have a digital Dictaphone with transcribing capabilities, providing me with texts to cut-n-paste into stuff I need to write. The background is that long drives often bring @@ -42,11 +42,11 @@ audio files and provide text representation of the speech in that audio recording. It handle multiple languages and according to its creators even can translate into a different language than the spoken one. I have not tested the latter feature. It can either use the CPU -or a GPU with CODA support. As far as I can tell, CODA in practice +or a GPU with CUDA support. As far as I can tell, CUDA in practice limit that feature to NVidia graphics cards. I have few of those, as they do not work great with free software drivers, and have not tested the GPU option. While looking into the matter, I did discover some -work to provide CODA support on non-NVidia GPUs, and some work with +work to provide CUDA support on non-NVidia GPUs, and some work with the library used by Whisper to port it to other GPUs, but have not spent much time looking into GPU support yet. I've so far used an old X220 laptop as my test machine, and only transcribed using its diff --git a/blog/index.html b/blog/index.html index 4b226301dd..298df8d13b 100644 --- a/blog/index.html +++ b/blog/index.html @@ -22,7 +22,7 @@

Speech to text, she APTly whispered, how hard can it be?
23rd April 2023
-

While visiting a convention during Eastern, it occurred to me that +

While visiting a convention during Easter, it occurred to me that it would be great if I could have a digital Dictaphone with transcribing capabilities, providing me with texts to cut-n-paste into stuff I need to write. The background is that long drives often bring @@ -35,11 +35,11 @@ audio files and provide text representation of the speech in that audio recording. It handle multiple languages and according to its creators even can translate into a different language than the spoken one. I have not tested the latter feature. It can either use the CPU -or a GPU with CODA support. As far as I can tell, CODA in practice +or a GPU with CUDA support. As far as I can tell, CUDA in practice limit that feature to NVidia graphics cards. I have few of those, as they do not work great with free software drivers, and have not tested the GPU option. While looking into the matter, I did discover some -work to provide CODA support on non-NVidia GPUs, and some work with +work to provide CUDA support on non-NVidia GPUs, and some work with the library used by Whisper to port it to other GPUs, but have not spent much time looking into GPU support yet. I've so far used an old X220 laptop as my test machine, and only transcribed using its diff --git a/blog/index.rss b/blog/index.rss index ceee023a61..642488cccf 100644 --- a/blog/index.rss +++ b/blog/index.rss @@ -11,7 +11,7 @@ https://people.skolelinux.org/pere/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html https://people.skolelinux.org/pere/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html Sun, 23 Apr 2023 09:40:00 +0200 - <p>While visiting a convention during Eastern, it occurred to me that + <p>While visiting a convention during Easter, it occurred to me that it would be great if I could have a digital Dictaphone with transcribing capabilities, providing me with texts to cut-n-paste into stuff I need to write. The background is that long drives often bring @@ -24,11 +24,11 @@ audio files and provide text representation of the speech in that audio recording. It handle multiple languages and according to its creators even can translate into a different language than the spoken one. I have not tested the latter feature. It can either use the CPU -or a GPU with CODA support. As far as I can tell, CODA in practice +or a GPU with CUDA support. As far as I can tell, CUDA in practice limit that feature to NVidia graphics cards. I have few of those, as they do not work great with free software drivers, and have not tested the GPU option. While looking into the matter, I did discover some -work to provide CODA support on non-NVidia GPUs, and some work with +work to provide CUDA support on non-NVidia GPUs, and some work with the library used by Whisper to port it to other GPUs, but have not spent much time looking into GPU support yet. I've so far used an old X220 laptop as my test machine, and only transcribed using its diff --git a/blog/tags/debian/debian.rss b/blog/tags/debian/debian.rss index a7faf23ff5..d42a2b07c1 100644 --- a/blog/tags/debian/debian.rss +++ b/blog/tags/debian/debian.rss @@ -11,7 +11,7 @@ https://people.skolelinux.org/pere/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html https://people.skolelinux.org/pere/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html Sun, 23 Apr 2023 09:40:00 +0200 - <p>While visiting a convention during Eastern, it occurred to me that + <p>While visiting a convention during Easter, it occurred to me that it would be great if I could have a digital Dictaphone with transcribing capabilities, providing me with texts to cut-n-paste into stuff I need to write. The background is that long drives often bring @@ -24,11 +24,11 @@ audio files and provide text representation of the speech in that audio recording. It handle multiple languages and according to its creators even can translate into a different language than the spoken one. I have not tested the latter feature. It can either use the CPU -or a GPU with CODA support. As far as I can tell, CODA in practice +or a GPU with CUDA support. As far as I can tell, CUDA in practice limit that feature to NVidia graphics cards. I have few of those, as they do not work great with free software drivers, and have not tested the GPU option. While looking into the matter, I did discover some -work to provide CODA support on non-NVidia GPUs, and some work with +work to provide CUDA support on non-NVidia GPUs, and some work with the library used by Whisper to port it to other GPUs, but have not spent much time looking into GPU support yet. I've so far used an old X220 laptop as my test machine, and only transcribed using its diff --git a/blog/tags/debian/index.html b/blog/tags/debian/index.html index ae3a686660..e21ef275a4 100644 --- a/blog/tags/debian/index.html +++ b/blog/tags/debian/index.html @@ -28,7 +28,7 @@ 23rd April 2023

-

While visiting a convention during Eastern, it occurred to me that +

While visiting a convention during Easter, it occurred to me that it would be great if I could have a digital Dictaphone with transcribing capabilities, providing me with texts to cut-n-paste into stuff I need to write. The background is that long drives often bring @@ -41,11 +41,11 @@ audio files and provide text representation of the speech in that audio recording. It handle multiple languages and according to its creators even can translate into a different language than the spoken one. I have not tested the latter feature. It can either use the CPU -or a GPU with CODA support. As far as I can tell, CODA in practice +or a GPU with CUDA support. As far as I can tell, CUDA in practice limit that feature to NVidia graphics cards. I have few of those, as they do not work great with free software drivers, and have not tested the GPU option. While looking into the matter, I did discover some -work to provide CODA support on non-NVidia GPUs, and some work with +work to provide CUDA support on non-NVidia GPUs, and some work with the library used by Whisper to port it to other GPUs, but have not spent much time looking into GPU support yet. I've so far used an old X220 laptop as my test machine, and only transcribed using its diff --git a/blog/tags/english/english.rss b/blog/tags/english/english.rss index c420a2f492..ec7adee9e1 100644 --- a/blog/tags/english/english.rss +++ b/blog/tags/english/english.rss @@ -11,7 +11,7 @@ https://people.skolelinux.org/pere/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html https://people.skolelinux.org/pere/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html Sun, 23 Apr 2023 09:40:00 +0200 - <p>While visiting a convention during Eastern, it occurred to me that + <p>While visiting a convention during Easter, it occurred to me that it would be great if I could have a digital Dictaphone with transcribing capabilities, providing me with texts to cut-n-paste into stuff I need to write. The background is that long drives often bring @@ -24,11 +24,11 @@ audio files and provide text representation of the speech in that audio recording. It handle multiple languages and according to its creators even can translate into a different language than the spoken one. I have not tested the latter feature. It can either use the CPU -or a GPU with CODA support. As far as I can tell, CODA in practice +or a GPU with CUDA support. As far as I can tell, CUDA in practice limit that feature to NVidia graphics cards. I have few of those, as they do not work great with free software drivers, and have not tested the GPU option. While looking into the matter, I did discover some -work to provide CODA support on non-NVidia GPUs, and some work with +work to provide CUDA support on non-NVidia GPUs, and some work with the library used by Whisper to port it to other GPUs, but have not spent much time looking into GPU support yet. I've so far used an old X220 laptop as my test machine, and only transcribed using its diff --git a/blog/tags/english/index.html b/blog/tags/english/index.html index 8a97c4abec..1a9c17811a 100644 --- a/blog/tags/english/index.html +++ b/blog/tags/english/index.html @@ -28,7 +28,7 @@ 23rd April 2023

-

While visiting a convention during Eastern, it occurred to me that +

While visiting a convention during Easter, it occurred to me that it would be great if I could have a digital Dictaphone with transcribing capabilities, providing me with texts to cut-n-paste into stuff I need to write. The background is that long drives often bring @@ -41,11 +41,11 @@ audio files and provide text representation of the speech in that audio recording. It handle multiple languages and according to its creators even can translate into a different language than the spoken one. I have not tested the latter feature. It can either use the CPU -or a GPU with CODA support. As far as I can tell, CODA in practice +or a GPU with CUDA support. As far as I can tell, CUDA in practice limit that feature to NVidia graphics cards. I have few of those, as they do not work great with free software drivers, and have not tested the GPU option. While looking into the matter, I did discover some -work to provide CODA support on non-NVidia GPUs, and some work with +work to provide CUDA support on non-NVidia GPUs, and some work with the library used by Whisper to port it to other GPUs, but have not spent much time looking into GPU support yet. I've so far used an old X220 laptop as my test machine, and only transcribed using its diff --git a/blog/tags/multimedia/index.html b/blog/tags/multimedia/index.html index 59489c67eb..ccc5dba787 100644 --- a/blog/tags/multimedia/index.html +++ b/blog/tags/multimedia/index.html @@ -28,7 +28,7 @@ 23rd April 2023

-

While visiting a convention during Eastern, it occurred to me that +

While visiting a convention during Easter, it occurred to me that it would be great if I could have a digital Dictaphone with transcribing capabilities, providing me with texts to cut-n-paste into stuff I need to write. The background is that long drives often bring @@ -41,11 +41,11 @@ audio files and provide text representation of the speech in that audio recording. It handle multiple languages and according to its creators even can translate into a different language than the spoken one. I have not tested the latter feature. It can either use the CPU -or a GPU with CODA support. As far as I can tell, CODA in practice +or a GPU with CUDA support. As far as I can tell, CUDA in practice limit that feature to NVidia graphics cards. I have few of those, as they do not work great with free software drivers, and have not tested the GPU option. While looking into the matter, I did discover some -work to provide CODA support on non-NVidia GPUs, and some work with +work to provide CUDA support on non-NVidia GPUs, and some work with the library used by Whisper to port it to other GPUs, but have not spent much time looking into GPU support yet. I've so far used an old X220 laptop as my test machine, and only transcribed using its diff --git a/blog/tags/multimedia/multimedia.rss b/blog/tags/multimedia/multimedia.rss index 158010009b..55491de344 100644 --- a/blog/tags/multimedia/multimedia.rss +++ b/blog/tags/multimedia/multimedia.rss @@ -11,7 +11,7 @@ https://people.skolelinux.org/pere/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html https://people.skolelinux.org/pere/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html Sun, 23 Apr 2023 09:40:00 +0200 - <p>While visiting a convention during Eastern, it occurred to me that + <p>While visiting a convention during Easter, it occurred to me that it would be great if I could have a digital Dictaphone with transcribing capabilities, providing me with texts to cut-n-paste into stuff I need to write. The background is that long drives often bring @@ -24,11 +24,11 @@ audio files and provide text representation of the speech in that audio recording. It handle multiple languages and according to its creators even can translate into a different language than the spoken one. I have not tested the latter feature. It can either use the CPU -or a GPU with CODA support. As far as I can tell, CODA in practice +or a GPU with CUDA support. As far as I can tell, CUDA in practice limit that feature to NVidia graphics cards. I have few of those, as they do not work great with free software drivers, and have not tested the GPU option. While looking into the matter, I did discover some -work to provide CODA support on non-NVidia GPUs, and some work with +work to provide CUDA support on non-NVidia GPUs, and some work with the library used by Whisper to port it to other GPUs, but have not spent much time looking into GPU support yet. I've so far used an old X220 laptop as my test machine, and only transcribed using its diff --git a/blog/tags/video/index.html b/blog/tags/video/index.html index 19fbc9cf41..7a54c82324 100644 --- a/blog/tags/video/index.html +++ b/blog/tags/video/index.html @@ -28,7 +28,7 @@ 23rd April 2023

-

While visiting a convention during Eastern, it occurred to me that +

While visiting a convention during Easter, it occurred to me that it would be great if I could have a digital Dictaphone with transcribing capabilities, providing me with texts to cut-n-paste into stuff I need to write. The background is that long drives often bring @@ -41,11 +41,11 @@ audio files and provide text representation of the speech in that audio recording. It handle multiple languages and according to its creators even can translate into a different language than the spoken one. I have not tested the latter feature. It can either use the CPU -or a GPU with CODA support. As far as I can tell, CODA in practice +or a GPU with CUDA support. As far as I can tell, CUDA in practice limit that feature to NVidia graphics cards. I have few of those, as they do not work great with free software drivers, and have not tested the GPU option. While looking into the matter, I did discover some -work to provide CODA support on non-NVidia GPUs, and some work with +work to provide CUDA support on non-NVidia GPUs, and some work with the library used by Whisper to port it to other GPUs, but have not spent much time looking into GPU support yet. I've so far used an old X220 laptop as my test machine, and only transcribed using its diff --git a/blog/tags/video/video.rss b/blog/tags/video/video.rss index 74c43b3eb2..959ad1da06 100644 --- a/blog/tags/video/video.rss +++ b/blog/tags/video/video.rss @@ -11,7 +11,7 @@ https://people.skolelinux.org/pere/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html https://people.skolelinux.org/pere/blog/Speech_to_text__she_APTly_whispered__how_hard_can_it_be_.html Sun, 23 Apr 2023 09:40:00 +0200 - <p>While visiting a convention during Eastern, it occurred to me that + <p>While visiting a convention during Easter, it occurred to me that it would be great if I could have a digital Dictaphone with transcribing capabilities, providing me with texts to cut-n-paste into stuff I need to write. The background is that long drives often bring @@ -24,11 +24,11 @@ audio files and provide text representation of the speech in that audio recording. It handle multiple languages and according to its creators even can translate into a different language than the spoken one. I have not tested the latter feature. It can either use the CPU -or a GPU with CODA support. As far as I can tell, CODA in practice +or a GPU with CUDA support. As far as I can tell, CUDA in practice limit that feature to NVidia graphics cards. I have few of those, as they do not work great with free software drivers, and have not tested the GPU option. While looking into the matter, I did discover some -work to provide CODA support on non-NVidia GPUs, and some work with +work to provide CUDA support on non-NVidia GPUs, and some work with the library used by Whisper to port it to other GPUs, but have not spent much time looking into GPU support yet. I've so far used an old X220 laptop as my test machine, and only transcribed using its