Text-to-Speech
F5-TTS
Files changed (1) hide show
  1. SWivid_F5-TTS.json +107 -0
SWivid_F5-TTS.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bomFormat": "CycloneDX",
3
+ "specVersion": "1.6",
4
+ "serialNumber": "urn:uuid:af7257f9-86de-47be-b728-482271c21016",
5
+ "version": 1,
6
+ "metadata": {
7
+ "timestamp": "2025-06-05T09:35:47.771137+00:00",
8
+ "component": {
9
+ "type": "machine-learning-model",
10
+ "bom-ref": "SWivid/F5-TTS-1eaa5074-7711-55bb-b142-7f1391dec9d2",
11
+ "name": "SWivid/F5-TTS",
12
+ "externalReferences": [
13
+ {
14
+ "url": "https://huggingface.co/SWivid/F5-TTS",
15
+ "type": "documentation"
16
+ }
17
+ ],
18
+ "modelCard": {
19
+ "modelParameters": {
20
+ "task": "text-to-speech",
21
+ "datasets": [
22
+ {
23
+ "ref": "amphion/Emilia-Dataset-a72e5559-5c47-57e2-9bae-a062ac838d0b"
24
+ }
25
+ ]
26
+ },
27
+ "properties": [
28
+ {
29
+ "name": "library_name",
30
+ "value": "f5-tts"
31
+ }
32
+ ]
33
+ },
34
+ "authors": [
35
+ {
36
+ "name": "SWivid"
37
+ }
38
+ ],
39
+ "licenses": [
40
+ {
41
+ "license": {
42
+ "id": "CC-BY-NC-4.0",
43
+ "url": "https://spdx.org/licenses/CC-BY-NC-4.0.html"
44
+ }
45
+ }
46
+ ],
47
+ "tags": [
48
+ "f5-tts",
49
+ "text-to-speech",
50
+ "dataset:amphion/Emilia-Dataset",
51
+ "arxiv:2410.06885",
52
+ "license:cc-by-nc-4.0",
53
+ "region:us"
54
+ ]
55
+ }
56
+ },
57
+ "components": [
58
+ {
59
+ "type": "data",
60
+ "bom-ref": "amphion/Emilia-Dataset-a72e5559-5c47-57e2-9bae-a062ac838d0b",
61
+ "name": "amphion/Emilia-Dataset",
62
+ "data": [
63
+ {
64
+ "type": "dataset",
65
+ "bom-ref": "amphion/Emilia-Dataset-a72e5559-5c47-57e2-9bae-a062ac838d0b",
66
+ "name": "amphion/Emilia-Dataset",
67
+ "contents": {
68
+ "url": "https://huggingface.co/datasets/amphion/Emilia-Dataset",
69
+ "properties": [
70
+ {
71
+ "name": "task_categories",
72
+ "value": "text-to-speech, automatic-speech-recognition"
73
+ },
74
+ {
75
+ "name": "language",
76
+ "value": "zh, en, ja, fr, de, ko"
77
+ },
78
+ {
79
+ "name": "size_categories",
80
+ "value": "10M<n<100M"
81
+ },
82
+ {
83
+ "name": "pretty_name",
84
+ "value": "Emilia"
85
+ },
86
+ {
87
+ "name": "license",
88
+ "value": "cc-by-4.0"
89
+ }
90
+ ]
91
+ },
92
+ "governance": {
93
+ "owners": [
94
+ {
95
+ "organization": {
96
+ "name": "amphion",
97
+ "url": "https://huggingface.co/amphion"
98
+ }
99
+ }
100
+ ]
101
+ },
102
+ "description": "\n\t\n\t\t\n\t\tEmilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation\n\t\n\n\nThis is the official repository \ud83d\udc51 for the Emilia dataset and the source code for the Emilia-Pipe speech data preprocessing pipeline. \n\n\n\n\t\n\t\t\n\t\tNews \ud83d\udd25\n\t\n\n\n2025/02/26: The Emilia-Large dataset, featuring over 200,000 hours of data, is now available!!! Emilia-Large combines the original 101k-hour Emilia dataset (licensed under CC BY-NC 4.0) with the brand-new 114k-hour Emilia-YODAS\u2026 See the full description on the dataset page: https://huggingface.co/datasets/amphion/Emilia-Dataset."
103
+ }
104
+ ]
105
+ }
106
+ ]
107
+ }