TASTomusan
commited on
Commit
·
ce6a243
1
Parent(s):
daeb2eb
Update README.md
Browse files
README.md
CHANGED
@@ -40,7 +40,23 @@ A:
|
|
40 |
> Go to "Files and versions", and then you'll find various voice models I had made in the past days (or months, or even years). Pick one (or many if you like), and
|
41 |
> then download at your own risk.
|
42 |
|
|
|
43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
|
45 |
• **_What are your software programs for working this models pack?_**
|
46 |
|
@@ -50,7 +66,9 @@ A:
|
|
50 |
> 2. RVC WebUI (0813) - for "model inference" and QA / QC (quality assurance / quality control or checks) before they're finalized.
|
51 |
> 3. Audacity Cross-Platform (64-bit on Windows) - for the usual audio editing and making the "audio datasets" for the planned voice models.
|
52 |
> 4. "Unspecified video-to-audio" converter (whether online or on local machine)
|
|
|
53 |
|
|
|
54 |
|
55 |
• **_How many days or months (or even years) did you worked on (a) voice model(s)?_**
|
56 |
|
@@ -58,7 +76,7 @@ A:
|
|
58 |
> It totally depends, including on whether it's going to be easy or very hard to find the proper sources found elsewhere in the Internet. Also the editing factors, whether
|
59 |
> again, ranging from very easy to very hard difficulty.
|
60 |
|
61 |
-
|
62 |
|
63 |
• **_Wait, why is "Instructions_Directions.txt" exists in this project? Some or most users doesn't seem to care on that file at all, but exactly what's that all about?_**
|
64 |
|
@@ -67,7 +85,7 @@ A:
|
|
67 |
people who wanted to read (and learn) more (no spoilers here) until through the bottommost part, then truly I recommend to read it first beforehand. They may download the mentioned file
|
68 |
as well on their own without compromises.
|
69 |
|
70 |
-
|
71 |
|
72 |
• **_And how about the "Reference" photo file in all voice models you'd uploaded?_**
|
73 |
|
@@ -76,7 +94,7 @@ A:
|
|
76 |
>
|
77 |
> Upon downloading voice model(s), it's clearly optional if you/they want to keep it, you/they may delete it. But for quality check reasons (not to get confused on whose voice(s) came from) I would recommend to keep it - it's just a single image file as is.
|
78 |
|
79 |
-
|
80 |
|
81 |
• **_What are these "sample / sample audio (language)" found in a voice model?_**
|
82 |
|
@@ -105,10 +123,11 @@ A:
|
|
105 |
> (and) Tagalog / Filipino
|
106 |
>
|
107 |
> <audio controls src="https://cdn-uploads.huggingface.co/production/uploads/656b6b210bbc114fe6ecc399/T1bg8oI_ma97T-s0WRUnO.wav"></audio>
|
108 |
-
>
|
|
|
109 |
> In that case, only 5 languages (of my own choice) are enough to actually consider. More than that is just too much to add, I guess.
|
110 |
|
111 |
-
|
112 |
|
113 |
• **_Do you see those "pickle" files? What does that mean?_**
|
114 |
|
@@ -116,9 +135,9 @@ A:
|
|
116 |
> They're just for serialization uses for ensuring they're safe (Punjabi) and no virus detected. Otherwise, those files will be marked as "Unsafe" (and should be deleted if found any) - you can read more here:
|
117 |
> **https://huggingface.co/docs/hub/security-malware**.
|
118 |
>
|
119 |
-
> Likewise, there's nothing to panic (or afraid of) on what you/they should do with having "pickle" files.
|
120 |
-
|
121 |
|
|
|
122 |
|
123 |
• **_Can these voice models be copyrighted (even in the near future)?_**
|
124 |
|
@@ -128,15 +147,15 @@ A:
|
|
128 |
> On the other hand, it's absolutely fine if you would credit me
|
129 |
fully so that people may know its true source / origin of those uploaded models. I would be truly appreciate it if you or someone did the proper crediting, so it's all up to you.
|
130 |
|
|
|
131 |
|
132 |
-
|
133 |
-
• **_Can we make request(s) to you, if possible?_**
|
134 |
|
135 |
A:
|
136 |
> Well, why not? I'll do my best as possible if there's enough time for me to do this so (aka "I shall see what I can do"). If you have any queries or other stuff in your mind to tell, please don't hesitate
|
137 |
(and feel free) to contact me via email: **[email protected]**
|
138 |
|
139 |
-
|
140 |
|
141 |
• **_Is there anything else we would like to know more about you?_**
|
142 |
|
@@ -157,12 +176,19 @@ A:
|
|
157 |
>
|
158 |
> And yeah, [this is my YouTube channel by the way](https://www.youtube.com/@TASTomusan).
|
159 |
|
|
|
160 |
|
161 |
Thanks for reading this README.md until the end. Take care and have a great day!
|
162 |
|
163 |
---------------------------------
|
164 |
|
165 |
|
166 |
-
Date created:
|
|
|
|
|
167 |
|
168 |
-
|
|
|
|
|
|
|
|
|
|
40 |
> Go to "Files and versions", and then you'll find various voice models I had made in the past days (or months, or even years). Pick one (or many if you like), and
|
41 |
> then download at your own risk.
|
42 |
|
43 |
+
<br>
|
44 |
|
45 |
+
• **_Upon downloading voice model(s), what are the contents based from your own work?_**
|
46 |
+
|
47 |
+
A:
|
48 |
+
> As follows: (inside the contents of "(Full voice model name.zip)" - usually quite bigger file size due to the following)
|
49 |
+
> 1. "Reference" image of the designated voice model
|
50 |
+
> 2. 5 sample audios (all are in .wav files)
|
51 |
+
> 3. (Voice model name) AI voice data.zip - should be extracted also
|
52 |
+
>
|
53 |
+
> A .pth file and an .index file
|
54 |
+
>
|
55 |
+
> <br>
|
56 |
+
> This is somewhat (truly) a unique style of from others. Yes, it might be complex to you for the first time (to understand and memorize), but you're about to master the sooner or later that it will be the
|
57 |
+
> default arrangement.
|
58 |
+
|
59 |
+
<br>
|
60 |
|
61 |
• **_What are your software programs for working this models pack?_**
|
62 |
|
|
|
66 |
> 2. RVC WebUI (0813) - for "model inference" and QA / QC (quality assurance / quality control or checks) before they're finalized.
|
67 |
> 3. Audacity Cross-Platform (64-bit on Windows) - for the usual audio editing and making the "audio datasets" for the planned voice models.
|
68 |
> 4. "Unspecified video-to-audio" converter (whether online or on local machine)
|
69 |
+
>
|
70 |
|
71 |
+
<br>
|
72 |
|
73 |
• **_How many days or months (or even years) did you worked on (a) voice model(s)?_**
|
74 |
|
|
|
76 |
> It totally depends, including on whether it's going to be easy or very hard to find the proper sources found elsewhere in the Internet. Also the editing factors, whether
|
77 |
> again, ranging from very easy to very hard difficulty.
|
78 |
|
79 |
+
<br>
|
80 |
|
81 |
• **_Wait, why is "Instructions_Directions.txt" exists in this project? Some or most users doesn't seem to care on that file at all, but exactly what's that all about?_**
|
82 |
|
|
|
85 |
people who wanted to read (and learn) more (no spoilers here) until through the bottommost part, then truly I recommend to read it first beforehand. They may download the mentioned file
|
86 |
as well on their own without compromises.
|
87 |
|
88 |
+
<br>
|
89 |
|
90 |
• **_And how about the "Reference" photo file in all voice models you'd uploaded?_**
|
91 |
|
|
|
94 |
>
|
95 |
> Upon downloading voice model(s), it's clearly optional if you/they want to keep it, you/they may delete it. But for quality check reasons (not to get confused on whose voice(s) came from) I would recommend to keep it - it's just a single image file as is.
|
96 |
|
97 |
+
<br>
|
98 |
|
99 |
• **_What are these "sample / sample audio (language)" found in a voice model?_**
|
100 |
|
|
|
123 |
> (and) Tagalog / Filipino
|
124 |
>
|
125 |
> <audio controls src="https://cdn-uploads.huggingface.co/production/uploads/656b6b210bbc114fe6ecc399/T1bg8oI_ma97T-s0WRUnO.wav"></audio>
|
126 |
+
>
|
127 |
+
> <br>
|
128 |
> In that case, only 5 languages (of my own choice) are enough to actually consider. More than that is just too much to add, I guess.
|
129 |
|
130 |
+
<br>
|
131 |
|
132 |
• **_Do you see those "pickle" files? What does that mean?_**
|
133 |
|
|
|
135 |
> They're just for serialization uses for ensuring they're safe (Punjabi) and no virus detected. Otherwise, those files will be marked as "Unsafe" (and should be deleted if found any) - you can read more here:
|
136 |
> **https://huggingface.co/docs/hub/security-malware**.
|
137 |
>
|
138 |
+
> Likewise, there's nothing to panic (or to be afraid of) on what you/they should do with having "pickle" files.
|
|
|
139 |
|
140 |
+
<br>
|
141 |
|
142 |
• **_Can these voice models be copyrighted (even in the near future)?_**
|
143 |
|
|
|
147 |
> On the other hand, it's absolutely fine if you would credit me
|
148 |
fully so that people may know its true source / origin of those uploaded models. I would be truly appreciate it if you or someone did the proper crediting, so it's all up to you.
|
149 |
|
150 |
+
<br>
|
151 |
|
152 |
+
• **_Can we make request(s) or ask more questions, if possible?_**
|
|
|
153 |
|
154 |
A:
|
155 |
> Well, why not? I'll do my best as possible if there's enough time for me to do this so (aka "I shall see what I can do"). If you have any queries or other stuff in your mind to tell, please don't hesitate
|
156 |
(and feel free) to contact me via email: **[email protected]**
|
157 |
|
158 |
+
<br>
|
159 |
|
160 |
• **_Is there anything else we would like to know more about you?_**
|
161 |
|
|
|
176 |
>
|
177 |
> And yeah, [this is my YouTube channel by the way](https://www.youtube.com/@TASTomusan).
|
178 |
|
179 |
+
<br>
|
180 |
|
181 |
Thanks for reading this README.md until the end. Take care and have a great day!
|
182 |
|
183 |
---------------------------------
|
184 |
|
185 |
|
186 |
+
Date created:
|
187 |
+
|
188 |
+
December 2, 2023 (9:50 PM - Dubai/Oman time) = **_Set as "Private"_**
|
189 |
|
190 |
+
December 2023 (- Dubai/Oman time) = **_Officially released_**
|
191 |
+
<br>
|
192 |
+
<br>
|
193 |
+
<br>
|
194 |
+
Last updated: December 2023 (- Dubai/Oman time)
|