-
Illustration is quite simple:
```
λ> import qualified Data.Massiv.Array as A
λ> xs = (A.generateM A.Seq 3 (\i -> [0..i]) :: [A.Array A.U Int Int])
λ> xs
[(Array U Seq (3)
[ 0,0,0 ]),(Array U…
-
### Pythran slower than Numpy...
We have a big performance issue with random number generation:
```
# tmp_rand.py
import numpy as np
# pythran export rand2d(int)
def rand2d(n):
return n…
-
For support and discussions, please use our [Discourse forums](https://discourse.mozilla.org/c/deep-speech).
If you've found a bug, or have a feature request, then please create an issue with the f…
-
The `PicovoiceCheetahASREngine` is super fast, but is not accurate based on my test.
Is it suitable to use Levenshtein distance as the WER?
From [Wikipedia](https://en.wikipedia.org/wiki/Word_er…
-
Right now, we only have 3K sentences or so.
Two possible new sources are
1. Wikimedia text
1. [BYU Corpus](http://corpus.byu.edu/)
1. [Leipzig Corpora](http://wortschatz.uni-leipzig.de/en/download/)
-
I am testing the mumax code and running some simple STT switching cases. I have noticed that the simulation on certain GPU cards (e.g. P40, P100) does not give any output or error (table.txt has only …
-
benchmark: https://blog.recast.ai/benchmarking-speech-recognition-api/
Can you guys please take a look at response times? I wonder if there is an issue in the SDK since I have been able to talk to …
-
One good feature for a solver is the ability to be compiled as a static executable.
Do you think it is possible to add such feature ?
Because I compile `moloss` on my machine and tried to run it o…
-
Aujourd'hui Jarvis supporte PocketSphinx pour la reconnaissance du mot clé "Jarvis" (uniquement).
Le dictionnaire utilisé est très limité (100 mots) car il est limité par la puissance du Raspberry Pi …
-
Kalliope is hanging on my RPi3 during playerback of mplayer. There is no error messages, the mplayer process seems to hang and kalliope is waiting for return of the process.
I can reproduce this wi…