-
type IsSpeaking
bool
type WhoIsSpeaking
uuid
known speakers
[chat on diarization embeddings](https://chatgpt.com/share/6704175b-9184-800f-bc01-2076a8af85bf)
[chat on running models locall…
-
The covenant is too america-centric and could be unapplicable e.g. in european law systems.
While in the US a nearly limitless freedom of speech is granted, in europe we dont have such limitless f…
-
max number of tokens I am able to run thru bark generate_text_semantic() is about 40, ~ 24 words or so.
I looked thru the code and noticed that generate_text_semantic() clips anything over 256 and…
xvdp updated
8 months ago
-
The pdf downloadable from Github (and distributed by my teacher for our course) has issues with Nordic letter (Ä. Ö, Å) representation.
When opening the pdf in chrome the letters render fine. However…
-
what is the training process and requirements?
-
There appear to be issues with weights in the grammar:
1. the grammar parser does not like weights very much (in fact, the lexer already doesn't like them).
According to https://www.w3.org/TR/20…
-
Hi
Where can I find the code needed to train the initial model and produce the model files?
-
Thank you for ESPnet team's continuous support. I have been using ESPnet and ESPnet2 for silent speech recogntion tasks for two years. (https://github.com/espnet/espnet/issues/1926)
I did visual sp…
-
Enable PyTorch Bfloat16 for CPU and add MKL-DNN bfloat16 optimization for Cooper Lake
## Motivation
Bfloat16 is a 16-bit floating point representation with same exponent bit-width as 32-bit floa…
-
## Week 4 : New York City Taxi Trip Duration
- [x] Dynamics of New York city - Animation
> - [x] Feature Engineering
> - [x] Clustering
> - [x] Find ride from one cluster to another
> - [x] Nei…