Spaces:
Paused
Paused
KEEP Listen: English README, no emoji
Browse files
README.md
CHANGED
|
@@ -1,20 +1,20 @@
|
|
| 1 |
---
|
| 2 |
-
title: KEEP
|
| 3 |
-
emoji: 👂
|
| 4 |
colorFrom: indigo
|
| 5 |
colorTo: green
|
| 6 |
sdk: gradio
|
| 7 |
app_file: app.py
|
| 8 |
pinned: false
|
| 9 |
license: other
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
-
# KEEP
|
| 13 |
|
| 14 |
-
|
| 15 |
-
(yes, no, up, down, left, right, on, off, stop, go)
|
| 16 |
|
| 17 |
-
-
|
| 18 |
-
-
|
| 19 |
|
| 20 |
-
|
|
|
|
| 1 |
---
|
| 2 |
+
title: KEEP Listen
|
|
|
|
| 3 |
colorFrom: indigo
|
| 4 |
colorTo: green
|
| 5 |
sdk: gradio
|
| 6 |
app_file: app.py
|
| 7 |
pinned: false
|
| 8 |
license: other
|
| 9 |
+
short_description: Recognizes 10 spoken English words as it listens.
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# KEEP Listen
|
| 13 |
|
| 14 |
+
AMEFORGE demo: a small model (about 265,000 parameters) recognizes **10 spoken English words**
|
| 15 |
+
(yes, no, up, down, left, right, on, off, stop, go) and shows how its confidence rises while listening.
|
| 16 |
|
| 17 |
+
- Measured accuracy: about 97% on never-heard voices (Google Speech Commands v0.02, official test lists).
|
| 18 |
+
- Limits: only these 10 words; any other sound is classified as one of them. Recognizing is not understanding.
|
| 19 |
|
| 20 |
+
Proprietary AMEFORGE model. Model weights and model code are not public.
|