Small correction!
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ metrics:
|
|
| 22 |
# Phonon-2
|
| 23 |
|
| 24 |
Phonon-2 is the most accurate open speech recognition model for English under 900 MB. Across the Open ASR Leaderboard's
|
| 25 |
-
seven English sets it averages 5.21 % word error, beating models multiple times its size in raw bytes.
|
| 26 |
Set for set it holds the accuracy of its 2.5 GB full-precision teacher, reaching 100.8 % of the teacher's word accuracy on
|
| 27 |
parliamentary speech and beating it on meetings, from a download 15 times smaller. Its encoder holds each weight at one of
|
| 28 |
five learned levels in about 2.1 bits.
|
|
|
|
| 22 |
# Phonon-2
|
| 23 |
|
| 24 |
Phonon-2 is the most accurate open speech recognition model for English under 900 MB. Across the Open ASR Leaderboard's
|
| 25 |
+
seven English sets it averages 5.21 % word error rate (WER), beating models multiple times its size in raw bytes.
|
| 26 |
Set for set it holds the accuracy of its 2.5 GB full-precision teacher, reaching 100.8 % of the teacher's word accuracy on
|
| 27 |
parliamentary speech and beating it on meetings, from a download 15 times smaller. Its encoder holds each weight at one of
|
| 28 |
five learned levels in about 2.1 bits.
|