Hugging Face's logo

Intel
/
versatile_audio_super_resolution_openvino

Model card Files
xet
Community
RyanMetcalfeInt8 commited on
Commit
ef350dd
·
1 Parent(s): 9a97d7f

extract zips, mel_24000_cpu.raw -> .bin, rm zips

Browse files
Files changed (17) hide show
  1. versatile_audio_sr_base_openvino_models.zip → audiosr_decoder.bin +2 -2
  2. audiosr_decoder.xml +0 -0
  3. versatile_audio_sr_ddpm_basic_openvino_models.zip → audiosr_encoder.bin +2 -2
  4. audiosr_encoder.xml +0 -0
  5. versatile_audio_sr_ddpm_speech_openvino_models.zip → basic/ddpm.bin +2 -2
  6. basic/ddpm.xml +0 -0
  7. mel_24000_cpu.bin +3 -0
  8. post_quant_conv.bin +3 -0
  9. post_quant_conv.xml +160 -0
  10. quant_conv.bin +3 -0
  11. quant_conv.xml +160 -0
  12. speech/ddpm.bin +3 -0
  13. speech/ddpm.xml +0 -0
  14. vae_feature_extract.bin +3 -0
  15. vae_feature_extract.xml +0 -0
  16. vocoder.bin +3 -0
  17. vocoder.xml +0 -0
versatile_audio_sr_base_openvino_models.zip → audiosr_decoder.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4058862616e8eaa157a6a69d75daff49b63f997c69e59887c77a04ce6840d86
3
- size 930565310
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f15dd621d5ffb191f1dbb5540b7c75301e8769ccbe062942b74a81e98ac2dd2
3
+ size 267047980
audiosr_decoder.xml ADDED
The diff for this file is too large to render. See raw diff
 
versatile_audio_sr_ddpm_basic_openvino_models.zip → audiosr_encoder.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:382e0693e35e4bbeae1a0f3223954250e13427108ae16c0fe8f786489bbe2767
3
- size 473639145
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb70d3baff6a5859a8f05f6ab7b3a13d5d0b23540758c78ccf91b0ccd4f83d6
3
+ size 180020602
audiosr_encoder.xml ADDED
The diff for this file is too large to render. See raw diff
 
versatile_audio_sr_ddpm_speech_openvino_models.zip → basic/ddpm.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f44ee433da9e1aa6dd948142d81523c7a58213acfa0699a4014e1f6d30e8a349
3
- size 473616589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03fa2b86f718e23b0c81e1ef481c1d75c87d3d6eb949cdfe06ca351b8f509d8d
3
+ size 516390728
basic/ddpm.xml ADDED
The diff for this file is too large to render. See raw diff
 
mel_24000_cpu.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dd24b6b1a81dc8f70ed479186fe66b1ccb4fc2dcffc3133dfd01daa93618c1d
3
+ size 1049600
post_quant_conv.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe865e2ad452ac5de682a7d9afecd685da2fca328ff453d0575fd75196f809c0
3
+ size 544
post_quant_conv.xml ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="torch_jit" version="11">
3
+ <layers>
4
+ <layer id="0" name="in" type="Parameter" version="opset1">
5
+ <data shape="1,16,128,32" element_type="f32" />
6
+ <output>
7
+ <port id="0" precision="FP32" names="in">
8
+ <dim>1</dim>
9
+ <dim>16</dim>
10
+ <dim>128</dim>
11
+ <dim>32</dim>
12
+ </port>
13
+ </output>
14
+ </layer>
15
+ <layer id="1" name="weight_compressed" type="Const" version="opset1">
16
+ <data element_type="f16" shape="16, 16, 1, 1" offset="0" size="512" />
17
+ <output>
18
+ <port id="0" precision="FP16">
19
+ <dim>16</dim>
20
+ <dim>16</dim>
21
+ <dim>1</dim>
22
+ <dim>1</dim>
23
+ </port>
24
+ </output>
25
+ </layer>
26
+ <layer id="2" name="weight" type="Convert" version="opset1">
27
+ <data destination_type="f32" />
28
+ <rt_info>
29
+ <attribute name="decompression" version="0" />
30
+ </rt_info>
31
+ <input>
32
+ <port id="0" precision="FP16">
33
+ <dim>16</dim>
34
+ <dim>16</dim>
35
+ <dim>1</dim>
36
+ <dim>1</dim>
37
+ </port>
38
+ </input>
39
+ <output>
40
+ <port id="1" precision="FP32" names="weight">
41
+ <dim>16</dim>
42
+ <dim>16</dim>
43
+ <dim>1</dim>
44
+ <dim>1</dim>
45
+ </port>
46
+ </output>
47
+ </layer>
48
+ <layer id="3" name="/Conv/WithoutBiases" type="Convolution" version="opset1">
49
+ <data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
50
+ <input>
51
+ <port id="0" precision="FP32">
52
+ <dim>1</dim>
53
+ <dim>16</dim>
54
+ <dim>128</dim>
55
+ <dim>32</dim>
56
+ </port>
57
+ <port id="1" precision="FP32">
58
+ <dim>16</dim>
59
+ <dim>16</dim>
60
+ <dim>1</dim>
61
+ <dim>1</dim>
62
+ </port>
63
+ </input>
64
+ <output>
65
+ <port id="2" precision="FP32">
66
+ <dim>1</dim>
67
+ <dim>16</dim>
68
+ <dim>128</dim>
69
+ <dim>32</dim>
70
+ </port>
71
+ </output>
72
+ </layer>
73
+ <layer id="4" name="Reshape_16_compressed" type="Const" version="opset1">
74
+ <data element_type="f16" shape="1, 16, 1, 1" offset="512" size="32" />
75
+ <output>
76
+ <port id="0" precision="FP16">
77
+ <dim>1</dim>
78
+ <dim>16</dim>
79
+ <dim>1</dim>
80
+ <dim>1</dim>
81
+ </port>
82
+ </output>
83
+ </layer>
84
+ <layer id="5" name="Reshape_16" type="Convert" version="opset1">
85
+ <data destination_type="f32" />
86
+ <rt_info>
87
+ <attribute name="decompression" version="0" />
88
+ </rt_info>
89
+ <input>
90
+ <port id="0" precision="FP16">
91
+ <dim>1</dim>
92
+ <dim>16</dim>
93
+ <dim>1</dim>
94
+ <dim>1</dim>
95
+ </port>
96
+ </input>
97
+ <output>
98
+ <port id="1" precision="FP32">
99
+ <dim>1</dim>
100
+ <dim>16</dim>
101
+ <dim>1</dim>
102
+ <dim>1</dim>
103
+ </port>
104
+ </output>
105
+ </layer>
106
+ <layer id="6" name="out" type="Add" version="opset1">
107
+ <data auto_broadcast="numpy" />
108
+ <input>
109
+ <port id="0" precision="FP32">
110
+ <dim>1</dim>
111
+ <dim>16</dim>
112
+ <dim>128</dim>
113
+ <dim>32</dim>
114
+ </port>
115
+ <port id="1" precision="FP32">
116
+ <dim>1</dim>
117
+ <dim>16</dim>
118
+ <dim>1</dim>
119
+ <dim>1</dim>
120
+ </port>
121
+ </input>
122
+ <output>
123
+ <port id="2" precision="FP32" names="out">
124
+ <dim>1</dim>
125
+ <dim>16</dim>
126
+ <dim>128</dim>
127
+ <dim>32</dim>
128
+ </port>
129
+ </output>
130
+ </layer>
131
+ <layer id="7" name="out/sink_port_0" type="Result" version="opset1">
132
+ <input>
133
+ <port id="0" precision="FP32">
134
+ <dim>1</dim>
135
+ <dim>16</dim>
136
+ <dim>128</dim>
137
+ <dim>32</dim>
138
+ </port>
139
+ </input>
140
+ </layer>
141
+ </layers>
142
+ <edges>
143
+ <edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
144
+ <edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
145
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="1" />
146
+ <edge from-layer="3" from-port="2" to-layer="6" to-port="0" />
147
+ <edge from-layer="4" from-port="0" to-layer="5" to-port="0" />
148
+ <edge from-layer="5" from-port="1" to-layer="6" to-port="1" />
149
+ <edge from-layer="6" from-port="2" to-layer="7" to-port="0" />
150
+ </edges>
151
+ <rt_info>
152
+ <MO_version value="2024.4.0-16579-c3152d32c9c-releases/2024/4" />
153
+ <Runtime_version value="2024.4.0-16579-c3152d32c9c-releases/2024/4" />
154
+ <conversion_parameters>
155
+ <input_model value="DIR\post_quant_conv.onnx" />
156
+ <is_python_api_used value="False" />
157
+ </conversion_parameters>
158
+ <legacy_frontend value="False" />
159
+ </rt_info>
160
+ </net>
quant_conv.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a10eb725d47b58dd4edf72284681c78edcd56c83386e2665d3f7dcdf22ff96f
3
+ size 2112
quant_conv.xml ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="torch_jit" version="11">
3
+ <layers>
4
+ <layer id="0" name="h" type="Parameter" version="opset1">
5
+ <data shape="1,32,128,32" element_type="f32" />
6
+ <output>
7
+ <port id="0" precision="FP32" names="h">
8
+ <dim>1</dim>
9
+ <dim>32</dim>
10
+ <dim>128</dim>
11
+ <dim>32</dim>
12
+ </port>
13
+ </output>
14
+ </layer>
15
+ <layer id="1" name="weight_compressed" type="Const" version="opset1">
16
+ <data element_type="f16" shape="32, 32, 1, 1" offset="0" size="2048" />
17
+ <output>
18
+ <port id="0" precision="FP16">
19
+ <dim>32</dim>
20
+ <dim>32</dim>
21
+ <dim>1</dim>
22
+ <dim>1</dim>
23
+ </port>
24
+ </output>
25
+ </layer>
26
+ <layer id="2" name="weight" type="Convert" version="opset1">
27
+ <data destination_type="f32" />
28
+ <rt_info>
29
+ <attribute name="decompression" version="0" />
30
+ </rt_info>
31
+ <input>
32
+ <port id="0" precision="FP16">
33
+ <dim>32</dim>
34
+ <dim>32</dim>
35
+ <dim>1</dim>
36
+ <dim>1</dim>
37
+ </port>
38
+ </input>
39
+ <output>
40
+ <port id="1" precision="FP32" names="weight">
41
+ <dim>32</dim>
42
+ <dim>32</dim>
43
+ <dim>1</dim>
44
+ <dim>1</dim>
45
+ </port>
46
+ </output>
47
+ </layer>
48
+ <layer id="3" name="/Conv/WithoutBiases" type="Convolution" version="opset1">
49
+ <data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
50
+ <input>
51
+ <port id="0" precision="FP32">
52
+ <dim>1</dim>
53
+ <dim>32</dim>
54
+ <dim>128</dim>
55
+ <dim>32</dim>
56
+ </port>
57
+ <port id="1" precision="FP32">
58
+ <dim>32</dim>
59
+ <dim>32</dim>
60
+ <dim>1</dim>
61
+ <dim>1</dim>
62
+ </port>
63
+ </input>
64
+ <output>
65
+ <port id="2" precision="FP32">
66
+ <dim>1</dim>
67
+ <dim>32</dim>
68
+ <dim>128</dim>
69
+ <dim>32</dim>
70
+ </port>
71
+ </output>
72
+ </layer>
73
+ <layer id="4" name="Reshape_16_compressed" type="Const" version="opset1">
74
+ <data element_type="f16" shape="1, 32, 1, 1" offset="2048" size="64" />
75
+ <output>
76
+ <port id="0" precision="FP16">
77
+ <dim>1</dim>
78
+ <dim>32</dim>
79
+ <dim>1</dim>
80
+ <dim>1</dim>
81
+ </port>
82
+ </output>
83
+ </layer>
84
+ <layer id="5" name="Reshape_16" type="Convert" version="opset1">
85
+ <data destination_type="f32" />
86
+ <rt_info>
87
+ <attribute name="decompression" version="0" />
88
+ </rt_info>
89
+ <input>
90
+ <port id="0" precision="FP16">
91
+ <dim>1</dim>
92
+ <dim>32</dim>
93
+ <dim>1</dim>
94
+ <dim>1</dim>
95
+ </port>
96
+ </input>
97
+ <output>
98
+ <port id="1" precision="FP32">
99
+ <dim>1</dim>
100
+ <dim>32</dim>
101
+ <dim>1</dim>
102
+ <dim>1</dim>
103
+ </port>
104
+ </output>
105
+ </layer>
106
+ <layer id="6" name="moments" type="Add" version="opset1">
107
+ <data auto_broadcast="numpy" />
108
+ <input>
109
+ <port id="0" precision="FP32">
110
+ <dim>1</dim>
111
+ <dim>32</dim>
112
+ <dim>128</dim>
113
+ <dim>32</dim>
114
+ </port>
115
+ <port id="1" precision="FP32">
116
+ <dim>1</dim>
117
+ <dim>32</dim>
118
+ <dim>1</dim>
119
+ <dim>1</dim>
120
+ </port>
121
+ </input>
122
+ <output>
123
+ <port id="2" precision="FP32" names="moments">
124
+ <dim>1</dim>
125
+ <dim>32</dim>
126
+ <dim>128</dim>
127
+ <dim>32</dim>
128
+ </port>
129
+ </output>
130
+ </layer>
131
+ <layer id="7" name="moments/sink_port_0" type="Result" version="opset1">
132
+ <input>
133
+ <port id="0" precision="FP32">
134
+ <dim>1</dim>
135
+ <dim>32</dim>
136
+ <dim>128</dim>
137
+ <dim>32</dim>
138
+ </port>
139
+ </input>
140
+ </layer>
141
+ </layers>
142
+ <edges>
143
+ <edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
144
+ <edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
145
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="1" />
146
+ <edge from-layer="3" from-port="2" to-layer="6" to-port="0" />
147
+ <edge from-layer="4" from-port="0" to-layer="5" to-port="0" />
148
+ <edge from-layer="5" from-port="1" to-layer="6" to-port="1" />
149
+ <edge from-layer="6" from-port="2" to-layer="7" to-port="0" />
150
+ </edges>
151
+ <rt_info>
152
+ <MO_version value="2024.4.0-16579-c3152d32c9c-releases/2024/4" />
153
+ <Runtime_version value="2024.4.0-16579-c3152d32c9c-releases/2024/4" />
154
+ <conversion_parameters>
155
+ <input_model value="DIR\quant_conv.onnx" />
156
+ <is_python_api_used value="False" />
157
+ </conversion_parameters>
158
+ <legacy_frontend value="False" />
159
+ </rt_info>
160
+ </net>
speech/ddpm.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3565cdfca685b7d6bbce89257dd62c54827bb5b5452ce5bf5439e271fa2d2c8d
3
+ size 516390728
speech/ddpm.xml ADDED
The diff for this file is too large to render. See raw diff
 
vae_feature_extract.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cb961e646544a8de08cddef328aabe222e7e701794bb37193cd651f522a188f
3
+ size 180022744
vae_feature_extract.xml ADDED
The diff for this file is too large to render. See raw diff
 
vocoder.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33a9c6375fe33bc652f8e22d4fc0b5317351f9acdaa7121bf92c9b1e594fdd8f
3
+ size 380563784
vocoder.xml ADDED
The diff for this file is too large to render. See raw diff