Updates the README
Browse files
README.md
CHANGED
@@ -21,14 +21,14 @@ metrics:
|
|
21 |
- BAK
|
22 |
- OVRL
|
23 |
model-index:
|
24 |
-
- name:
|
25 |
results:
|
26 |
- task:
|
27 |
name: Speech Enhancement
|
28 |
type: speech-enhancement
|
29 |
dataset:
|
30 |
name: Voicebank-DEMAND
|
31 |
-
type:
|
32 |
split: test-set
|
33 |
args:
|
34 |
language: en
|
@@ -42,6 +42,12 @@ model-index:
|
|
42 |
- name: DNSMOS OVRL
|
43 |
type: ovrl
|
44 |
value: '3.205'
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
---
|
46 |
# Open-UNIVERSE: Generative Speech Enhancement with Score-based Diffusion and Adversarial Training
|
47 |
|
@@ -71,8 +77,9 @@ python -m pip install .
|
|
71 |
|
72 |
Then the models can be used as follows.
|
73 |
```sh
|
74 |
-
# UNIVERSE++
|
75 |
-
python -m open_universe.bin.enhance <input/folder> <output/folder>
|
|
|
76 |
|
77 |
# UNIVERSE
|
78 |
python -m open_universe.bin.enhance <input/folder> <output/folder> \
|
|
|
21 |
- BAK
|
22 |
- OVRL
|
23 |
model-index:
|
24 |
+
- name: universe++
|
25 |
results:
|
26 |
- task:
|
27 |
name: Speech Enhancement
|
28 |
type: speech-enhancement
|
29 |
dataset:
|
30 |
name: Voicebank-DEMAND
|
31 |
+
type: demand
|
32 |
split: test-set
|
33 |
args:
|
34 |
language: en
|
|
|
42 |
- name: DNSMOS OVRL
|
43 |
type: ovrl
|
44 |
value: '3.205'
|
45 |
+
- name: PESQ
|
46 |
+
type: pesq
|
47 |
+
value: 3.017
|
48 |
+
- name: SI-SDR
|
49 |
+
type: si-sdr
|
50 |
+
value: 18.629
|
51 |
---
|
52 |
# Open-UNIVERSE: Generative Speech Enhancement with Score-based Diffusion and Adversarial Training
|
53 |
|
|
|
77 |
|
78 |
Then the models can be used as follows.
|
79 |
```sh
|
80 |
+
# UNIVERSE++ (default model)
|
81 |
+
python -m open_universe.bin.enhance <input/folder> <output/folder> \
|
82 |
+
--model line-corporation/open-universe:plusplus
|
83 |
|
84 |
# UNIVERSE
|
85 |
python -m open_universe.bin.enhance <input/folder> <output/folder> \
|