Spaces:
Runtime error
Runtime error
Commit
·
150fe29
1
Parent(s):
cd2339e
new model - Azure Cobalt (#4)
Browse files- new model - Azure Cobalt (e0d3ffd3485825d03fc722e2e608115ec86d9a0b)
Co-authored-by: Aster <Asteriski@users.noreply.huggingface.co>
- Azure.ckpt +3 -0
- Azure.py +48 -0
- config.yaml +9 -1
Azure.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96460bc65045cdf0552c235872996f24c5adf3f83373cd594ea8970160bb384c
|
| 3 |
+
size 409441960
|
Azure.py
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from fish_diffusion.datasets.hifisinger import HiFiSVCDataset
|
| 2 |
+
from fish_diffusion.datasets.utils import get_datasets_from_subfolder
|
| 3 |
+
|
| 4 |
+
_base_ = [
|
| 5 |
+
"./_base_/archs/hifi_svc.py",
|
| 6 |
+
"./_base_/trainers/base.py",
|
| 7 |
+
"./_base_/schedulers/exponential.py",
|
| 8 |
+
"./_base_/datasets/hifi_svc.py",
|
| 9 |
+
]
|
| 10 |
+
|
| 11 |
+
speaker_mapping = {
|
| 12 |
+
"Placeholder": 0,
|
| 13 |
+
}
|
| 14 |
+
|
| 15 |
+
model = dict(
|
| 16 |
+
type="HiFiSVC",
|
| 17 |
+
speaker_encoder=dict(
|
| 18 |
+
input_size=len(speaker_mapping),
|
| 19 |
+
),
|
| 20 |
+
)
|
| 21 |
+
|
| 22 |
+
preprocessing = dict(
|
| 23 |
+
text_features_extractor=dict(
|
| 24 |
+
type="ContentVec",
|
| 25 |
+
),
|
| 26 |
+
pitch_extractor=dict(
|
| 27 |
+
type="CrepePitchExtractor",
|
| 28 |
+
keep_zeros=False,
|
| 29 |
+
f0_min=40.0,
|
| 30 |
+
f0_max=2000.0,
|
| 31 |
+
),
|
| 32 |
+
energy_extractor=dict(
|
| 33 |
+
type="RMSEnergyExtractor",
|
| 34 |
+
),
|
| 35 |
+
augmentations=[
|
| 36 |
+
dict(
|
| 37 |
+
type="FixedPitchShifting",
|
| 38 |
+
key_shifts=[-5.0, 5.0],
|
| 39 |
+
probability=0.75,
|
| 40 |
+
),
|
| 41 |
+
],
|
| 42 |
+
)
|
| 43 |
+
|
| 44 |
+
trainer = dict(
|
| 45 |
+
# Disable gradient clipping, which is not supported by custom optimization
|
| 46 |
+
gradient_clip_val=None,
|
| 47 |
+
max_steps=1000000,
|
| 48 |
+
)
|
config.yaml
CHANGED
|
@@ -83,4 +83,12 @@ models:
|
|
| 83 |
readme: |
|
| 84 |
This model is trained on a datset known as C and released under the [CC-BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license.
|
| 85 |
It has a whispery, fluttery voice.
|
| 86 |
-
default_speaker: "c"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
readme: |
|
| 84 |
This model is trained on a datset known as C and released under the [CC-BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license.
|
| 85 |
It has a whispery, fluttery voice.
|
| 86 |
+
default_speaker: "c"
|
| 87 |
+
|
| 88 |
+
- name: "Azure Cobalt (Feminine)"
|
| 89 |
+
config: configs/Azure.py
|
| 90 |
+
checkpoint: checkpoints/Azure.ckpt
|
| 91 |
+
readme: |
|
| 92 |
+
This model is trained on a dataset known as Azure Cobalt and released under the [CC-BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license.
|
| 93 |
+
It has a whispery, fluttery voice.
|
| 94 |
+
default_speaker: "azure"
|