Add model card (Not complete)
Browse files
README.md
CHANGED
@@ -1,3 +1,239 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
metrics:
|
6 |
+
- wer
|
7 |
+
pipeline_tag: text-to-speech
|
8 |
+
tags:
|
9 |
+
- text-to-speech
|
10 |
+
- audio
|
11 |
---
|
12 |
+
|
13 |
+
# Model Card for TorToiSe
|
14 |
+
|
15 |
+
<!-- Provide a quick summary of what the model is/does. [Optional] -->
|
16 |
+
Tortoise is a text-to-speech program built with the following priorities:
|
17 |
+
|
18 |
+
1. Strong multi-voice capabilities.
|
19 |
+
2. Highly realistic prosody and intonation.
|
20 |
+
|
21 |
+
# Table of Contents
|
22 |
+
|
23 |
+
- [Model Card for TorToiSe](#model-card-for--model_id-)
|
24 |
+
- [Table of Contents](#table-of-contents)
|
25 |
+
- [Table of Contents](#table-of-contents-1)
|
26 |
+
- [Model Details](#model-details)
|
27 |
+
- [Model Description](#model-description)
|
28 |
+
- [Uses](#uses)
|
29 |
+
- [Direct Use](#direct-use)
|
30 |
+
- [Out-of-Scope Use](#out-of-scope-use)
|
31 |
+
- [Bias, Risks, and Limitations](#bias-risks-and-limitations)
|
32 |
+
- [Recommendations](#recommendations)
|
33 |
+
- [Training Details](#training-details)
|
34 |
+
- [Training Data](#training-data)
|
35 |
+
- [Training Procedure](#training-procedure)
|
36 |
+
- [Preprocessing](#preprocessing)
|
37 |
+
- [Speeds, Sizes, Times](#speeds-sizes-times)
|
38 |
+
- [Evaluation](#evaluation)
|
39 |
+
- [Testing Data, Factors & Metrics](#testing-data-factors--metrics)
|
40 |
+
- [Testing Data](#testing-data)
|
41 |
+
- [Factors](#factors)
|
42 |
+
- [Metrics](#metrics)
|
43 |
+
- [Results](#results)
|
44 |
+
- [Model Examination](#model-examination)
|
45 |
+
- [Environmental Impact](#environmental-impact)
|
46 |
+
- [Model Architecture and Objective](#model-architecture-and-objective)
|
47 |
+
- [Compute Infrastructure](#compute-infrastructure)
|
48 |
+
- [Hardware](#hardware)
|
49 |
+
- [Software](#software)
|
50 |
+
- [Citation](#citation)
|
51 |
+
- [Model Card Contact](#model-card-contact)
|
52 |
+
- [How to Get Started with the Model](#how-to-get-started-with-the-model)
|
53 |
+
|
54 |
+
|
55 |
+
# Model Details
|
56 |
+
|
57 |
+
## Model Description
|
58 |
+
|
59 |
+
<!-- Provide a longer summary of what this model is/does. -->
|
60 |
+
Tortoise is a text-to-speech program built with the following priorities:
|
61 |
+
|
62 |
+
1. Strong multi-voice capabilities.
|
63 |
+
2. Highly realistic prosody and intonation.
|
64 |
+
|
65 |
+
|
66 |
+
- **Developed by:** James Betker
|
67 |
+
- **Model type:** Language model
|
68 |
+
- **Language(s) (NLP):** en
|
69 |
+
- **License:** apache-2.0
|
70 |
+
- **Resources for more information:**
|
71 |
+
- [GitHub Repo](https://github.com/152334H/tortoise-tts-fast)
|
72 |
+
|
73 |
+
|
74 |
+
# Uses
|
75 |
+
|
76 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
77 |
+
|
78 |
+
## Direct Use
|
79 |
+
|
80 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
81 |
+
<!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->
|
82 |
+
|
83 |
+
|
84 |
+
|
85 |
+
## Out-of-Scope Use
|
86 |
+
|
87 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
88 |
+
<!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->
|
89 |
+
|
90 |
+
|
91 |
+
|
92 |
+
|
93 |
+
# Bias, Risks, and Limitations
|
94 |
+
|
95 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
96 |
+
|
97 |
+
|
98 |
+
|
99 |
+
## Recommendations
|
100 |
+
|
101 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
102 |
+
|
103 |
+
|
104 |
+
|
105 |
+
# Training Details
|
106 |
+
|
107 |
+
## Training Data
|
108 |
+
|
109 |
+
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
110 |
+
|
111 |
+
More information on training data needed
|
112 |
+
|
113 |
+
|
114 |
+
## Training Procedure
|
115 |
+
|
116 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
117 |
+
|
118 |
+
### Preprocessing
|
119 |
+
|
120 |
+
More information needed
|
121 |
+
|
122 |
+
### Speeds, Sizes, Times
|
123 |
+
|
124 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
125 |
+
|
126 |
+
More information needed
|
127 |
+
|
128 |
+
# Evaluation
|
129 |
+
|
130 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
131 |
+
|
132 |
+
## Testing Data, Factors & Metrics
|
133 |
+
|
134 |
+
### Testing Data
|
135 |
+
|
136 |
+
<!-- This should link to a Data Card if possible. -->
|
137 |
+
|
138 |
+
More information needed
|
139 |
+
|
140 |
+
|
141 |
+
### Factors
|
142 |
+
|
143 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
144 |
+
|
145 |
+
More information needed
|
146 |
+
|
147 |
+
### Metrics
|
148 |
+
|
149 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
150 |
+
|
151 |
+
More information needed
|
152 |
+
|
153 |
+
## Results
|
154 |
+
|
155 |
+
More information needed
|
156 |
+
|
157 |
+
# Model Examination
|
158 |
+
|
159 |
+
More information needed
|
160 |
+
|
161 |
+
# Environmental Impact
|
162 |
+
|
163 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
164 |
+
|
165 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
166 |
+
|
167 |
+
- **Hardware Type:** More information needed
|
168 |
+
- **Hours used:** More information needed
|
169 |
+
- **Cloud Provider:** More information needed
|
170 |
+
- **Compute Region:** More information needed
|
171 |
+
- **Carbon Emitted:** More information needed
|
172 |
+
|
173 |
+
# Technical Specifications [optional]
|
174 |
+
|
175 |
+
## Model Architecture and Objective
|
176 |
+
|
177 |
+
More information needed
|
178 |
+
|
179 |
+
## Compute Infrastructure
|
180 |
+
|
181 |
+
More information needed
|
182 |
+
|
183 |
+
### Hardware
|
184 |
+
|
185 |
+
More information needed
|
186 |
+
|
187 |
+
### Software
|
188 |
+
|
189 |
+
More information needed
|
190 |
+
|
191 |
+
# Citation
|
192 |
+
|
193 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
194 |
+
|
195 |
+
**BibTeX:**
|
196 |
+
|
197 |
+
Betker, J. (2022). TorToiSe text-to-speech (Version 2.0) [Computer software]. https://github.com/neonbjb/tortoise-tts
|
198 |
+
|
199 |
+
**APA:**
|
200 |
+
|
201 |
+
@software{Betker_TorToiSe_text-to-speech_2022,
|
202 |
+
author = {Betker, James},
|
203 |
+
month = {4},
|
204 |
+
title = {{TorToiSe text-to-speech}},
|
205 |
+
url = {https://github.com/neonbjb/tortoise-tts},
|
206 |
+
version = {2.0},
|
207 |
+
year = {2022}
|
208 |
+
}
|
209 |
+
|
210 |
+
# Glossary [optional]
|
211 |
+
|
212 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
213 |
+
|
214 |
+
More information needed
|
215 |
+
|
216 |
+
# More Information [optional]
|
217 |
+
|
218 |
+
More information needed
|
219 |
+
|
220 |
+
# Model Card Authors [optional]
|
221 |
+
|
222 |
+
<!-- This section provides another layer of transparency and accountability. Whose views is this model card representing? How many voices were included in its construction? Etc. -->
|
223 |
+
|
224 |
+
Gatozu35
|
225 |
+
|
226 |
+
# Model Card Contact
|
227 |
+
|
228 |
+
Use the discussion tab
|
229 |
+
|
230 |
+
# How to Get Started with the Model
|
231 |
+
|
232 |
+
Use the code below to get started with the model.
|
233 |
+
|
234 |
+
<details>
|
235 |
+
<summary> Click to expand </summary>
|
236 |
+
|
237 |
+
More information needed
|
238 |
+
|
239 |
+
</details>
|