Hugging Face's logo

second-state
/
OuteTTS-0.3-500M-GGUF

Text-to-Speech
GGUF
qwen2
Inference Endpoints
conversational
Model card Files Community
apepkuss79 commited on
Commit
c8f2f04
·
verified ·
1 Parent(s): 82a5bb2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +94 -86
README.md CHANGED
@@ -1,87 +1,95 @@
1
- ---
2
- base_model: OuteAI/OuteTTS-0.3-500M
3
- license: cc-by-nc-4.0
4
- model_creator: OuteAI
5
- model_name: OuteTTS-0.3-500M
6
- quantized_by: Second State Inc.
7
- ---
8
-
9
- <!-- header start -->
10
- <!-- 200823 -->
11
- <div style="width: auto; margin-left: auto; margin-right: auto">
12
- <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
13
- </div>
14
- <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
15
- <!-- header end -->
16
-
17
- # OuteTTS-0.3-500M-GGUF
18
-
19
- ## Original Model
20
-
21
- [OuteAI/OuteTTS-0.3-500M](https://huggingface.co/OuteAI/OuteTTS-0.3-500M)
22
-
23
- ## Run with LlamaEdge
24
-
25
- - LlamaEdge version: coming soon
26
-
27
- <!-- - LlamaEdge version: [v0.14.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.3) and above -->
28
-
29
- <!-- - Prompt template
30
-
31
- - Prompt type: `llama-3-chat`
32
-
33
- - Prompt string
34
-
35
- ```text
36
- <|begin_of_text|><|start_header_id|>system<|end_header_id|>
37
-
38
- {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
39
-
40
- {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
41
-
42
- {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
43
-
44
- {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
45
- ```
46
-
47
- - Context size: `8192`
48
-
49
- - Run as LlamaEdge service
50
-
51
- ```bash
52
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:OuteTTS-0.3-500M-Q5_K_M.gguf \
53
- llama-api-server.wasm \
54
- --model-name OuteTTS-0.3-500M \
55
- --prompt-template llama-3-chat \
56
- --ctx-size 8192
57
- ```
58
-
59
- - Run as LlamaEdge command app
60
-
61
- ```bash
62
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:OuteTTS-0.3-500M-Q5_K_M.gguf \
63
- llama-chat.wasm \
64
- --prompt-template llama-3-chat \
65
- --ctx-size 8192
66
- ``` -->
67
-
68
- ## Quantized GGUF Models
69
-
70
- | Name | Quant method | Bits | Size | Use case |
71
- | ---- | ---- | ---- | ---- | ----- |
72
- | [OuteTTS-0.3-500M-Q2_K.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q2_K.gguf) | Q2_K | 2 | 344 MB| smallest, significant quality loss - not recommended for most purposes |
73
- | [OuteTTS-0.3-500M-Q3_K_L.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q3_K_L.gguf) | Q3_K_L | 3 | 375 MB| small, substantial quality loss |
74
- | [OuteTTS-0.3-500M-Q3_K_M.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q3_K_M.gguf) | Q3_K_M | 3 | 361 MB| very small, high quality loss |
75
- | [OuteTTS-0.3-500M-Q3_K_S.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q3_K_S.gguf) | Q3_K_S | 3 | 344 MB| very small, high quality loss |
76
- | [OuteTTS-0.3-500M-Q4_0.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q4_0.gguf) | Q4_0 | 4 | 358 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
77
- | [OuteTTS-0.3-500M-Q4_K_M.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q4_K_M.gguf) | Q4_K_M | 4 | 403 MB| medium, balanced quality - recommended |
78
- | [OuteTTS-0.3-500M-Q4_K_S.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q4_K_S.gguf) | Q4_K_S | 4 | 391 MB| small, greater quality loss |
79
- | [OuteTTS-0.3-500M-Q5_0.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q5_0.gguf) | Q5_0 | 5 | 402 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
80
- | [OuteTTS-0.3-500M-Q5_K_M.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q5_K_M.gguf) | Q5_K_M | 5 | 426 MB| large, very low quality loss - recommended |
81
- | [OuteTTS-0.3-500M-Q5_K_S.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q5_K_S.gguf) | Q5_K_S | 5 | 418 MB| large, low quality loss - recommended |
82
- | [OuteTTS-0.3-500M-Q6_K.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q6_K.gguf) | Q6_K | 6 | 511 MB| very large, extremely low quality loss |
83
- | [OuteTTS-0.3-500M-Q8_0.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q8_0.gguf) | Q8_0 | 8 | 537 MB| very large, extremely low quality loss - not recommended |
84
- | [OuteTTS-0.3-500M-f16.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-f16.gguf) | f16 | 16 | 1.00 GB| |
85
- | [wavtokenizer-large-75-ggml-f16.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/wavtokenizer-large-75-ggml-f16.gguf) | f16 | 16 | 1.00 GB| |
86
-
 
 
 
 
 
 
 
 
87
  *Quantized with llama.cpp b4497*
 
1
+ ---
2
+ base_model: OuteAI/OuteTTS-0.3-500M
3
+ license: cc-by-nc-4.0
4
+ model_creator: OuteAI
5
+ model_name: OuteTTS-0.3-500M
6
+ quantized_by: Second State Inc.
7
+ language:
8
+ - en
9
+ - zh
10
+ - ja
11
+ - ko
12
+ - fr
13
+ - de
14
+ pipeline_tag: text-to-speech
15
+ ---
16
+
17
+ <!-- header start -->
18
+ <!-- 200823 -->
19
+ <div style="width: auto; margin-left: auto; margin-right: auto">
20
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
21
+ </div>
22
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
23
+ <!-- header end -->
24
+
25
+ # OuteTTS-0.3-500M-GGUF
26
+
27
+ ## Original Model
28
+
29
+ [OuteAI/OuteTTS-0.3-500M](https://huggingface.co/OuteAI/OuteTTS-0.3-500M)
30
+
31
+ ## Run with LlamaEdge
32
+
33
+ - LlamaEdge version: coming soon
34
+
35
+ <!-- - LlamaEdge version: [v0.14.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.3) and above -->
36
+
37
+ <!-- - Prompt template
38
+
39
+ - Prompt type: `llama-3-chat`
40
+
41
+ - Prompt string
42
+
43
+ ```text
44
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
45
+
46
+ {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
47
+
48
+ {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
49
+
50
+ {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
51
+
52
+ {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
53
+ ```
54
+
55
+ - Context size: `8192`
56
+
57
+ - Run as LlamaEdge service
58
+
59
+ ```bash
60
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:OuteTTS-0.3-500M-Q5_K_M.gguf \
61
+ llama-api-server.wasm \
62
+ --model-name OuteTTS-0.3-500M \
63
+ --prompt-template llama-3-chat \
64
+ --ctx-size 8192
65
+ ```
66
+
67
+ - Run as LlamaEdge command app
68
+
69
+ ```bash
70
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:OuteTTS-0.3-500M-Q5_K_M.gguf \
71
+ llama-chat.wasm \
72
+ --prompt-template llama-3-chat \
73
+ --ctx-size 8192
74
+ ``` -->
75
+
76
+ ## Quantized GGUF Models
77
+
78
+ | Name | Quant method | Bits | Size | Use case |
79
+ | ---- | ---- | ---- | ---- | ----- |
80
+ | [OuteTTS-0.3-500M-Q2_K.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q2_K.gguf) | Q2_K | 2 | 344 MB| smallest, significant quality loss - not recommended for most purposes |
81
+ | [OuteTTS-0.3-500M-Q3_K_L.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q3_K_L.gguf) | Q3_K_L | 3 | 375 MB| small, substantial quality loss |
82
+ | [OuteTTS-0.3-500M-Q3_K_M.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q3_K_M.gguf) | Q3_K_M | 3 | 361 MB| very small, high quality loss |
83
+ | [OuteTTS-0.3-500M-Q3_K_S.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q3_K_S.gguf) | Q3_K_S | 3 | 344 MB| very small, high quality loss |
84
+ | [OuteTTS-0.3-500M-Q4_0.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q4_0.gguf) | Q4_0 | 4 | 358 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
85
+ | [OuteTTS-0.3-500M-Q4_K_M.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q4_K_M.gguf) | Q4_K_M | 4 | 403 MB| medium, balanced quality - recommended |
86
+ | [OuteTTS-0.3-500M-Q4_K_S.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q4_K_S.gguf) | Q4_K_S | 4 | 391 MB| small, greater quality loss |
87
+ | [OuteTTS-0.3-500M-Q5_0.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q5_0.gguf) | Q5_0 | 5 | 402 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
88
+ | [OuteTTS-0.3-500M-Q5_K_M.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q5_K_M.gguf) | Q5_K_M | 5 | 426 MB| large, very low quality loss - recommended |
89
+ | [OuteTTS-0.3-500M-Q5_K_S.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q5_K_S.gguf) | Q5_K_S | 5 | 418 MB| large, low quality loss - recommended |
90
+ | [OuteTTS-0.3-500M-Q6_K.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q6_K.gguf) | Q6_K | 6 | 511 MB| very large, extremely low quality loss |
91
+ | [OuteTTS-0.3-500M-Q8_0.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-Q8_0.gguf) | Q8_0 | 8 | 537 MB| very large, extremely low quality loss - not recommended |
92
+ | [OuteTTS-0.3-500M-f16.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/OuteTTS-0.3-500M-f16.gguf) | f16 | 16 | 1.00 GB| |
93
+ | [wavtokenizer-large-75-ggml-f16.gguf](https://huggingface.co/second-state/OuteTTS-0.3-500M-GGUF/blob/main/wavtokenizer-large-75-ggml-f16.gguf) | f16 | 16 | 1.00 GB| |
94
+
95
  *Quantized with llama.cpp b4497*