diff options
| author | Moonchild <moonchild@palemoon.org> | 2020-05-20 10:19:04 +0000 |
|---|---|---|
| committer | Moonchild <moonchild@palemoon.org> | 2020-05-20 14:04:17 +0000 |
| commit | 99c2e698d2a3c56649e42d8d2133706cd8c9501e (patch) | |
| tree | 85be449d772eb57860f0f386efb4bc1e790fd498 /dom/media/webspeech/recognition/models/en-US/feat.params | |
| parent | 15ac4021b06d549e47c9e2efc9364a9eb96bfe82 (diff) | |
| download | UXP-99c2e698d2a3c56649e42d8d2133706cd8c9501e.tar UXP-99c2e698d2a3c56649e42d8d2133706cd8c9501e.tar.gz UXP-99c2e698d2a3c56649e42d8d2133706cd8c9501e.tar.lz UXP-99c2e698d2a3c56649e42d8d2133706cd8c9501e.tar.xz UXP-99c2e698d2a3c56649e42d8d2133706cd8c9501e.zip | |
Issue #1538 - remove speech recognition engine
This removes speech recognition, pocketsphinx, training models
and the speech automated test interface.
This also re-establishes proper use of MOZ_WEBSPEECH to work
for the speech API (synthesis part only) that was a broken mess
before, with some synth parts being always built, some parts
being built only with it enabled and recognition parts being
dependent on it. I'm pretty sure it'd be totally busted if you'd
ever have tried building without MOZ_WEBPEECH before.
Tested that synthesis still works as-intended.
This resolves #1538
Diffstat (limited to 'dom/media/webspeech/recognition/models/en-US/feat.params')
| -rw-r--r-- | dom/media/webspeech/recognition/models/en-US/feat.params | 12 |
1 files changed, 0 insertions, 12 deletions
diff --git a/dom/media/webspeech/recognition/models/en-US/feat.params b/dom/media/webspeech/recognition/models/en-US/feat.params deleted file mode 100644 index 324987f32..000000000 --- a/dom/media/webspeech/recognition/models/en-US/feat.params +++ /dev/null @@ -1,12 +0,0 @@ --lowerf 130 --upperf 3700 --nfilt 20 --transform dct --lifter 22 --feat 1s_c_d_dd --svspec 0-12/13-25/26-38 --agc none --cmn current --varnorm no --cmninit 30.09,0.49,5.51,7.43,-2.39,-1.64,-4.71,0.03,-5.11,0.20,4.84,6.14,0.35 --model ptm |