-
Weekly summary, Jan 11-17 2024
This week, I have been concentrating on two items: better control of TTS, and an initial version of “Simple C-LARA”. Here are the details: TTS In response to Cathy’s post, pointing out that our default Google TTS isn’t very good, I did some work to integrate the OpenAI TTS engine, allowing the user to select… Continue reading
-
TTS options for C-LARA content development
In his last post Manny talked about the addition of Whisper TTS as an option to using Google. Admittedly prosody is better, but the only options are American accents and most people will at least want to be able to select a British accent for English – indeed, in our experience of being in Europe,… Continue reading
-
Improving C-LARA’s TTS
In her post two days ago, Cathy rightly said that the free Google TTS voice, which we’ve previously been using as our default, is not very good. I am in the middle of experimenting with connecting up various pieces of OpenAI software to C-LARA, so I thought I would make their TTS engine available too.… Continue reading
-
Beta-testing content creation on C-LARA
As a way to try out C-LARA’s content creation methods, I used English as the text language and annotations in French. For a prompt I asked for a poem to be generated based on the description I gave it of our new kitten Finley. First point: the prompt should be saved and isn’t. Second point:… Continue reading
-
Feedback on social network functionality
Claudia, Pauline, Branislav and I met up on Zoom yesterday and had a productive discussion about the initial C-LARA social network functionality. A general remark first: it’s clear that users have different requirements, and we must try to offer enough customisation options that users can easily make the platform conform to their own preferences. Here… Continue reading
-
Weekly summary: Jan 4-10, 2024
This week, I have been concentrating on three things: social network functionality, presentation, and an initial integration of DALL-E-3 into C-LARA. There have also been some interesting discussions with Claudia, Christèle and Pauline about moving towards initial user testing. Social network I’ve already posted about the social network part here. We now have a substantially… Continue reading
-
C-LARA social network: current state of play, Jan 8 2024
The last couple of days, ChatGPT-4 and I have been concentrating on adding basic social network functionality to C-LARA. I should say that nearly all of the work has been done by Chat. The features we’re adding are simple and standard, they are implemented using mainstream Django design patterns, and on this kind of territory… Continue reading
-
Phonetic texts: current state of play, Jan 2 2024
We have several parallel discussions in progress about the phonetic texts. I thought it would be helpful to summarise where we are now, and what we’re planning to do next. By “phonetic text”, we mean a C-LARA text where the words have been divided into smaller units, each one associated with a phonetic value, and… Continue reading
-
Weekly summary, Dec 21-27 2023
Phonetic texts Claudia wondered if we could use the phonetic text functionality for Romanian. There is a phonetic lexicon available at ipa-dict, so it seemed straightforward, but in actual fact I found I had to fix a number of small issues. I have now installed the phonetic lexica for Romanian and Icelandic, and things are… Continue reading
-
Weekly summary, Dec 14-20
Phonetic texts This functionality now seems to be working well, we have been using it a lot during the last week. Alphabet book for Drehu Pauline and I have almost finished the alphabet book for Drehu – all that’s left is to upload the audio, Pauline and her colleague Fabrice are working on that now.… Continue reading
-
Subscribe
Subscribed
Already have a WordPress.com account? Log in now.
C-LARA 