YinuoGuo27 commited on
Commit
b0e2648
·
1 Parent(s): bab4de9
Files changed (3) hide show
  1. app.py +117 -0
  2. environment.yml +259 -0
  3. requirements.txt +333 -0
app.py ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import os, sys
2
+ import gradio as gr
3
+ from SadTalker.src.gradio_demo import SadTalker
4
+ from difpoint.inference import Inferencer
5
+ from TTS.api import TTS
6
+ import torch
7
+ import time
8
+ from flask import send_from_directory
9
+
10
+ # Device setup
11
+ device = "cuda" if torch.cuda.is_available() else "cpu"
12
+ torch.set_default_device(device)
13
+ tts = TTS('tts_models/multilingual/multi-dataset/your_tts').to(device)
14
+ tts.to(device)
15
+
16
+ result_dir = "results"
17
+
18
+ def predict(prompt, upload_reference_audio, microphone_reference_audio, reference_audio_type):
19
+ global result_dir
20
+ output_file_path = os.path.join(result_dir, 'output.wav')
21
+ if reference_audio_type == 'upload':
22
+ audio_file_pth = upload_reference_audio
23
+ elif reference_audio_type == 'microphone':
24
+ audio_file_pth = microphone_reference_audio
25
+ tts.tts_to_file(
26
+ text=prompt,
27
+ file_path=output_file_path,
28
+ speaker_wav=audio_file_pth,
29
+ language="en",
30
+ )
31
+ return gr.Audio(value=output_file_path, type='filepath')
32
+
33
+
34
+ def main(sadtaker_checkpoint_path=r"SadTalker/checkpoints", sadtalker_config_path=r"SadTalker/src/config"):
35
+ if torch.cuda.is_available():
36
+ device = "cuda"
37
+ else:
38
+ device = "cpu"
39
+ print('device is', device)
40
+ torch.set_default_device(device)
41
+ tts = TTS('tts_models/multilingual/multi-dataset/your_tts').to(device)
42
+ sad_talker = SadTalker(sadtaker_checkpoint_path, sadtalker_config_path, lazy_load=True)
43
+ kd_talker = Inferencer()
44
+
45
+ with gr.Blocks(analytics_enabled=False) as interface:
46
+ gr.Markdown(
47
+ """
48
+ <div align='center'>
49
+ <h2> Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait </h2>
50
+ <div style="display: flex; justify-content: center; align-items: center; gap: 20px;">
51
+ <img src='https://newstatic.dukekunshan.edu.cn/mainsite/2021/08/07161629/large_dku-Logo-e1649298929570.png' alt='Logo' width='150'/>
52
+ <img src='https://www.xjtlu.edu.cn/wp-content/uploads/2023/12/7c52fd62e9cf26cb493faa7f91c2782.png' width='250'/>
53
+ </div>
54
+ </div>
55
+ """
56
+ )
57
+ driven_audio_type = gr.State(value="upload")
58
+
59
+ with gr.Row():
60
+ with gr.Column(variant="panel"):
61
+ with gr.Tabs(elem_id="sadtalker_source_image"):
62
+ with gr.TabItem("Upload image"):
63
+ source_image = gr.Image(label="Source image", sources="upload", type="filepath", scale=256)
64
+
65
+ with gr.Tabs(elem_id="sadtalker_driven_audio"):
66
+ with gr.TabItem("Upload"):
67
+ upload_driven_audio = gr.Audio(label="Upload audio", sources="upload", type="filepath")
68
+ upload_driven_audio.change(lambda: "upload", outputs=driven_audio_type)
69
+ reference_audio_type = gr.State(value="upload")
70
+
71
+ with gr.TabItem("TTS"):
72
+ upload_reference_audio = gr.Audio(label="Upload Reference Audio", sources="upload", type="filepath")
73
+ upload_reference_audio.change(lambda: "upload", outputs=reference_audio_type)
74
+ microphone_reference_audio = gr.Audio(label="Recorded Reference Audio", sources="microphone", type="filepath")
75
+ microphone_reference_audio.change(lambda: "microphone", outputs=reference_audio_type)
76
+ input_text = gr.Textbox(
77
+ label="Generating audio from text",
78
+ lines=5,
79
+ placeholder="please enter some text here, we generate the audio from text using @Coqui.ai TTS."
80
+ )
81
+ tts_button = gr.Button("Generate audio", elem_id="sadtalker_audio_generate", variant="primary")
82
+ tts_driven_audio = gr.Audio(label="Synthesised Audio", type="filepath")
83
+ tts_button.click(fn=predict, inputs=[input_text, upload_reference_audio, microphone_reference_audio, reference_audio_type], outputs=[tts_driven_audio])
84
+ tts_button.click(lambda: "tts", outputs=driven_audio_type)
85
+
86
+ with gr.Column(variant="panel"):
87
+ gen_video = gr.Video(label="Generated video", format="mp4", width=256)
88
+ with gr.Tabs(elem_id="talker_checkbox"):
89
+ with gr.TabItem("KDTalker"):
90
+ smoothed_pitch = gr.Slider(minimum=0, maximum=1, step=0.1, label="Pitch", value=0.8)
91
+ smoothed_yaw = gr.Slider(minimum=0, maximum=1, step=0.1, label="Yaw", value=0.8)
92
+ smoothed_roll = gr.Slider(minimum=0, maximum=1, step=0.1, label="Roll", value=0.8)
93
+ smoothed_t = gr.Slider(minimum=0, maximum=1, step=0.1, label="T", value=0.8)
94
+ kd_submit = gr.Button("Generate", elem_id="kdtalker_generate", variant="primary")
95
+
96
+ kd_submit.click(
97
+ fn=kd_talker.generate_with_audio_img,
98
+ inputs=[
99
+ upload_driven_audio,
100
+ tts_driven_audio,
101
+ driven_audio_type,
102
+ source_image,
103
+ smoothed_pitch,
104
+ smoothed_yaw,
105
+ smoothed_roll,
106
+ smoothed_t,
107
+ ],
108
+ outputs=[gen_video]
109
+ )
110
+ return interface
111
+
112
+ if __name__ == "__main__":
113
+ os.environ["GRADIO_SERVER_PORT"] = "7860"
114
+ demo = main()
115
+ #demo.launch(server_name="0.0.0.0",ssl_certfile="cert.pem", ssl_keyfile="key.pem", ssl_verify=False, strict_cors = False)
116
+ demo.launch(server_name="0.0.0.0")
117
+
environment.yml ADDED
@@ -0,0 +1,259 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ name: FasterLivePortrait
2
+ channels:
3
+ - defaults
4
+ dependencies:
5
+ - bzip2=1.0.8
6
+ - ca-certificates=2024.7.2
7
+ - libffi=3.4.4
8
+ - openssl=3.0.15
9
+ - pip=24.2
10
+ - python=3.10.14
11
+ - setuptools=72.1.0
12
+ - sqlite=3.45.3
13
+ - tk=8.6.14
14
+ - vc=14.40
15
+ - vs2015_runtime=14.40.33807
16
+ - wheel=0.44.0
17
+ - xz=5.4.6
18
+ - zlib=1.2.13
19
+ - pip:
20
+ - absl-py==2.1.0
21
+ - addict==2.4.0
22
+ - aiofiles==23.2.1
23
+ - aiohappyeyeballs==2.4.0
24
+ - aiohttp==3.10.6
25
+ - aiosignal==1.3.1
26
+ - albucore==0.0.15
27
+ - albumentations==1.4.15
28
+ - altair==5.4.1
29
+ - annotated-types==0.7.0
30
+ - antlr4-python3-runtime==4.9.3
31
+ - anyascii==0.3.2
32
+ - anyio==4.4.0
33
+ - async-timeout==4.0.3
34
+ - attrs==24.2.0
35
+ - audioread==3.0.1
36
+ - babel==2.16.0
37
+ - bangla==0.0.2
38
+ - basicsr==1.4.2
39
+ - blinker==1.8.2
40
+ - blis==0.7.11
41
+ - bnnumerizer==0.0.2
42
+ - bnunicodenormalizer==0.1.7
43
+ - catalogue==2.0.10
44
+ - cerberus==1.3.5
45
+ - certifi==2024.8.30
46
+ - cffi==1.17.1
47
+ - charset-normalizer==3.3.2
48
+ - click==8.1.7
49
+ - cloudpathlib==0.19.0
50
+ - colorama==0.4.6
51
+ - coloredlogs==15.0.1
52
+ - confection==0.1.5
53
+ - contourpy==1.2.1
54
+ - coqpit==0.0.17
55
+ - cycler==0.12.1
56
+ - cymem==2.0.8
57
+ - cython==3.0.11
58
+ - dateparser==1.1.8
59
+ - decorator==5.1.1
60
+ - diffusers==0.30.3
61
+ - dlib==19.24.6
62
+ - docopt==0.6.2
63
+ - docstring-parser==0.16
64
+ - easydict==1.13
65
+ - einops==0.8.0
66
+ - einops-exts==0.0.4
67
+ - encodec==0.1.1
68
+ - eval-type-backport==0.2.0
69
+ - exceptiongroup==1.2.2
70
+ - facexlib==0.3.0
71
+ - fastapi==0.114.2
72
+ - ffmpeg==1.4
73
+ - ffmpeg-python==0.2.0
74
+ - ffmpy==0.4.0
75
+ - filelock==3.16.0
76
+ - filterpy==1.4.5
77
+ - flask==3.0.3
78
+ - flatbuffers==24.3.25
79
+ - fonttools==4.53.1
80
+ - frozenlist==1.4.1
81
+ - fsspec==2024.9.0
82
+ - future==1.0.0
83
+ - g2pkk==0.1.2
84
+ - gfpgan==1.3.8
85
+ - gradio==3.50.0
86
+ - gradio-client==0.6.1
87
+ - grpcio==1.66.1
88
+ - gruut==2.2.3
89
+ - gruut-ipa==0.13.0
90
+ - gruut-lang-de==2.0.1
91
+ - gruut-lang-en==2.0.1
92
+ - gruut-lang-es==2.0.1
93
+ - gruut-lang-fr==2.0.2
94
+ - h11==0.14.0
95
+ - hangul-romanize==0.1.0
96
+ - httpcore==1.0.5
97
+ - httpx==0.27.2
98
+ - huggingface-hub==0.24.7
99
+ - humanfriendly==10.0
100
+ - idna==3.10
101
+ - imageio==2.35.1
102
+ - imageio-ffmpeg==0.5.1
103
+ - importlib-metadata==8.5.0
104
+ - importlib-resources==6.4.5
105
+ - inflect==7.4.0
106
+ - iniconfig==2.0.0
107
+ - inquirerpy==0.3.4
108
+ - insightface==0.7.3
109
+ - itsdangerous==2.2.0
110
+ - jamo==0.4.1
111
+ - jax==0.4.31
112
+ - jaxlib==0.4.31
113
+ - jieba==0.42.1
114
+ - jinja2==3.1.4
115
+ - joblib==1.4.2
116
+ - jsonlines==1.2.0
117
+ - jsonschema==4.23.0
118
+ - jsonschema-specifications==2023.12.1
119
+ - kiwisolver==1.4.7
120
+ - kornia==0.7.3
121
+ - kornia-rs==0.1.5
122
+ - langcodes==3.4.0
123
+ - language-data==1.2.0
124
+ - lazy-loader==0.4
125
+ - librosa==0.10.0
126
+ - llvmlite==0.43.0
127
+ - lmdb==1.5.1
128
+ - mako==1.3.5
129
+ - marisa-trie==1.2.0
130
+ - markdown==3.7
131
+ - markdown-it-py==3.0.0
132
+ - markupsafe==2.1.5
133
+ - matplotlib==3.8.4
134
+ - mdurl==0.1.2
135
+ - mediapipe==0.10.14
136
+ - ml-dtypes==0.5.0
137
+ - more-itertools==10.5.0
138
+ - mpmath==1.3.0
139
+ - msgpack==1.1.0
140
+ - multidict==6.1.0
141
+ - murmurhash==1.0.10
142
+ - mutagen==1.47.0
143
+ - narwhals==1.8.3
144
+ - networkx==2.8.8
145
+ - nltk==3.9.1
146
+ - num2words==0.5.13
147
+ - numba==0.60.0
148
+ - numpy==1.26.4
149
+ - nvidia-cuda-runtime-cu12==12.6.68
150
+ - omegaconf==2.3.0
151
+ - onnx==1.16.2
152
+ - onnxruntime==1.19.2
153
+ - onnxruntime-gpu==1.17.0
154
+ - opencv-contrib-python==4.10.0.84
155
+ - opencv-python==4.10.0.84
156
+ - opencv-python-headless==4.10.0.84
157
+ - opt-einsum==3.3.0
158
+ - orjson==3.10.7
159
+ - packaging==24.1
160
+ - pandas==1.5.3
161
+ - pfzy==0.3.4
162
+ - pillow==10.4.0
163
+ - platformdirs==4.3.3
164
+ - pluggy==1.5.0
165
+ - pooch==1.8.2
166
+ - preshed==3.0.9
167
+ - prettytable==3.11.0
168
+ - prompt-toolkit==3.0.47
169
+ - protobuf==4.25.4
170
+ - psutil==6.0.0
171
+ - pycparser==2.22
172
+ - pycuda==2024.1.2
173
+ - pydantic==2.9.1
174
+ - pydantic-core==2.23.3
175
+ - pydub==0.25.1
176
+ - pygments==2.18.0
177
+ - pykalman==0.9.7
178
+ - pynndescent==0.5.13
179
+ - pyparsing==3.1.4
180
+ - pypinyin==0.53.0
181
+ - pyreadline3==3.5.2
182
+ - pysbd==0.3.4
183
+ - pytest==8.3.3
184
+ - python-crfsuite==0.9.10
185
+ - python-dateutil==2.9.0.post0
186
+ - python-multipart==0.0.9
187
+ - pytools==2024.1.14
188
+ - pytz==2024.2
189
+ - pyyaml==6.0.2
190
+ - referencing==0.35.1
191
+ - regex==2024.9.11
192
+ - requests==2.32.3
193
+ - rich==13.8.1
194
+ - rotary-embedding-torch==0.8.3
195
+ - rpds-py==0.20.0
196
+ - ruff==0.6.5
197
+ - safetensors==0.4.5
198
+ - scikit-image==0.24.0
199
+ - scikit-learn==1.5.2
200
+ - scipy==1.11.4
201
+ - semantic-version==2.10.0
202
+ - shellingham==1.5.4
203
+ - shtab==1.7.1
204
+ - six==1.16.0
205
+ - smart-open==7.0.4
206
+ - sniffio==1.3.1
207
+ - sounddevice==0.5.0
208
+ - soundfile==0.12.1
209
+ - soxr==0.5.0.post1
210
+ - spacy==3.7.6
211
+ - spacy-legacy==3.0.12
212
+ - spacy-loggers==1.0.5
213
+ - srsly==2.4.8
214
+ - starlette==0.38.5
215
+ - sudachidict-core==20240716
216
+ - sudachipy==0.6.8
217
+ - sympy==1.13.2
218
+ - tb-nightly==2.18.0a20240924
219
+ - tensorboard==2.17.1
220
+ - tensorboard-data-server==0.7.2
221
+ - tensorrt==8.6.1
222
+ - tensorrt-cu12==10.4.0
223
+ - tensorrt-cu12-bindings==10.4.0
224
+ - tensorrt-cu12-libs==10.4.0
225
+ - thinc==8.2.5
226
+ - threadpoolctl==3.5.0
227
+ - tifffile==2024.8.30
228
+ - tokenizers==0.19.1
229
+ - tomli==2.0.1
230
+ - tomlkit==0.12.0
231
+ - torch==2.4.1+cu121
232
+ - torchaudio==2.4.1+cu121
233
+ - torchgeometry==0.1.2
234
+ - torchvision==0.19.1+cu121
235
+ - tqdm==4.66.5
236
+ - trainer==0.0.36
237
+ - transformers==4.44.2
238
+ - tts==0.22.0
239
+ - typeguard==4.3.0
240
+ - typer==0.12.5
241
+ - typing-extensions==4.12.2
242
+ - tyro==0.8.10
243
+ - tzdata==2024.1
244
+ - tzlocal==5.2
245
+ - umap-learn==0.5.6
246
+ - unidecode==1.3.8
247
+ - urllib3==2.2.3
248
+ - uvicorn==0.30.6
249
+ - wasabi==1.1.3
250
+ - wcwidth==0.2.13
251
+ - weasel==0.4.1
252
+ - websockets==11.0.3
253
+ - werkzeug==3.0.4
254
+ - wrapt==1.16.0
255
+ - yacs==0.1.8
256
+ - yapf==0.40.2
257
+ - yarl==1.12.1
258
+ - zipp==3.20.2
259
+ prefix: C:\Users\86136\anaconda3\envs\FasterLivePortrait
requirements.txt ADDED
@@ -0,0 +1,333 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ absl-py==2.1.0
2
+ accelerate==1.0.1
3
+ addict==2.4.0
4
+ aiofiles==23.2.1
5
+ aiohappyeyeballs==2.4.3
6
+ aiohttp==3.10.8
7
+ aiohttp-cors==0.7.0
8
+ aioice==0.9.0
9
+ aiortc==1.9.0
10
+ aiosignal==1.3.1
11
+ albucore==0.0.17
12
+ albumentations==1.4.16
13
+ altair==5.4.1
14
+ amqp==5.3.1
15
+ annotated-types==0.7.0
16
+ antlr4-python3-runtime==4.9.3
17
+ anyascii==0.3.2
18
+ anyio==4.6.0
19
+ asttokens @ file:///home/conda/feedstock_root/build_artifacts/asttokens_1698341106958/work
20
+ async-timeout==4.0.3
21
+ attrs==24.2.0
22
+ audioread==3.0.1
23
+ av==12.3.0
24
+ babel==2.16.0
25
+ bangla==0.0.2
26
+ basicsr==1.4.2
27
+ beautifulsoup4==4.12.3
28
+ bidict==0.23.1
29
+ billiard==4.2.1
30
+ blinker==1.8.2
31
+ blis==0.7.11
32
+ bnnumerizer==0.0.2
33
+ bnunicodenormalizer==0.1.7
34
+ bypy==1.8.5
35
+ catalogue==2.0.10
36
+ celery==5.4.0
37
+ certifi==2024.8.30
38
+ cffi==1.17.1
39
+ charset-normalizer==3.3.2
40
+ click==8.1.7
41
+ click-didyoumean==0.3.1
42
+ click-plugins==1.1.1
43
+ click-repl==0.3.0
44
+ clip==0.2.0
45
+ cloudpathlib==0.19.0
46
+ coloredlogs==15.0.1
47
+ comm @ file:///home/conda/feedstock_root/build_artifacts/comm_1710320294760/work
48
+ confection==0.1.5
49
+ contourpy==1.2.1
50
+ coqpit==0.0.17
51
+ cryptography==44.0.0
52
+ cycler==0.12.1
53
+ cymem==2.0.8
54
+ Cython==3.0.11
55
+ dateparser==1.1.8
56
+ debugpy @ file:///croot/debugpy_1690905042057/work
57
+ decorator==4.4.2
58
+ diffusers==0.30.3
59
+ dill==0.3.9
60
+ dlib==19.24.6
61
+ dnspython==2.7.0
62
+ docker-pycreds==0.4.0
63
+ docopt==0.6.2
64
+ docstring_parser==0.16
65
+ easydict==1.13
66
+ edge-tts==7.0.0
67
+ einops==0.8.0
68
+ einops-exts==0.0.4
69
+ encodec==0.1.1
70
+ entrypoints @ file:///home/conda/feedstock_root/build_artifacts/entrypoints_1643888246732/work
71
+ eval_type_backport==0.2.0
72
+ exceptiongroup @ file:///home/conda/feedstock_root/build_artifacts/exceptiongroup_1720869315914/work
73
+ executing @ file:///home/conda/feedstock_root/build_artifacts/executing_1725214404607/work
74
+ facexlib==0.3.0
75
+ fastapi==0.115.4
76
+ ffmpeg==1.4
77
+ ffmpeg-python==0.2.0
78
+ ffmpy==0.4.0
79
+ filelock==3.16.1
80
+ filterpy==1.4.5
81
+ Flask==3.0.3
82
+ Flask-Cors==5.0.0
83
+ Flask-SocketIO==5.5.1
84
+ Flask-Sockets==0.2.1
85
+ flatbuffers==24.3.25
86
+ fonttools==4.54.1
87
+ frozenlist==1.4.1
88
+ fsspec==2024.9.0
89
+ future==1.0.0
90
+ g2pkk==0.1.2
91
+ gdown==5.2.0
92
+ gevent==24.11.1
93
+ gevent-websocket==0.10.1
94
+ gfpgan==1.3.8
95
+ gitdb==4.0.11
96
+ GitPython==3.1.43
97
+ google-crc32c==1.6.0
98
+ gradio==5.4.0
99
+ gradio_client==1.4.2
100
+ greenlet==3.1.1
101
+ grpcio==1.66.2
102
+ gruut==2.2.3
103
+ gruut-ipa==0.13.0
104
+ gruut_lang_de==2.0.1
105
+ gruut_lang_en==2.0.1
106
+ gruut_lang_es==2.0.1
107
+ gruut_lang_fr==2.0.2
108
+ h11==0.14.0
109
+ hangul-romanize==0.1.0
110
+ httpcore==1.0.5
111
+ httpx==0.27.2
112
+ huggingface-hub==0.25.1
113
+ humanfriendly==10.0
114
+ hydra-core==1.3.2
115
+ idna==3.10
116
+ ifaddr==0.2.0
117
+ imageio==2.35.1
118
+ imageio-ffmpeg==0.5.1
119
+ importlib_metadata==8.5.0
120
+ importlib_resources==6.4.5
121
+ imutils==0.5.4
122
+ inflect==7.4.0
123
+ inquirerpy==0.3.4
124
+ insightface==0.7.3
125
+ ipykernel @ file:///home/conda/feedstock_root/build_artifacts/ipykernel_1719845459717/work
126
+ ipython==8.27.0
127
+ ipywidgets==8.1.5
128
+ itsdangerous==2.2.0
129
+ jamo==0.4.1
130
+ jax==0.4.33
131
+ jaxlib==0.4.33
132
+ jedi @ file:///home/conda/feedstock_root/build_artifacts/jedi_1696326070614/work
133
+ jieba==0.42.1
134
+ Jinja2==3.1.4
135
+ joblib==1.4.2
136
+ jsonlines==1.2.0
137
+ jsonschema==4.23.0
138
+ jsonschema-specifications==2023.12.1
139
+ jupyter-client @ file:///home/conda/feedstock_root/build_artifacts/jupyter_client_1654730843242/work
140
+ jupyter_core @ file:///home/conda/feedstock_root/build_artifacts/jupyter_core_1727163409502/work
141
+ jupyterlab_widgets==3.0.13
142
+ kiwisolver==1.4.7
143
+ kombu==5.4.2
144
+ kornia==0.7.3
145
+ kornia_rs==0.1.5
146
+ langcodes==3.4.1
147
+ language_data==1.2.0
148
+ lazy_loader==0.4
149
+ librosa==0.10.0
150
+ llvmlite==0.43.0
151
+ lmdb==1.5.1
152
+ lpips==0.1.4
153
+ Mako==1.3.5
154
+ marisa-trie==1.2.0
155
+ Markdown==3.7
156
+ markdown-it-py==3.0.0
157
+ MarkupSafe==2.1.5
158
+ matplotlib==3.8.4
159
+ matplotlib-inline @ file:///home/conda/feedstock_root/build_artifacts/matplotlib-inline_1713250518406/work
160
+ mdurl==0.1.2
161
+ mediapipe==0.10.15
162
+ ml_dtypes==0.5.0
163
+ more-itertools==10.5.0
164
+ moviepy==1.0.3
165
+ mpmath==1.3.0
166
+ msgpack==1.1.0
167
+ multidict==6.1.0
168
+ multiprocess==0.70.17
169
+ munch==4.0.0
170
+ murmurhash==1.0.10
171
+ narwhals==1.8.4
172
+ nest_asyncio @ file:///home/conda/feedstock_root/build_artifacts/nest-asyncio_1705850609492/work
173
+ networkx==2.8.8
174
+ ninja==1.11.1.3
175
+ nltk==3.9.1
176
+ num2words==0.5.13
177
+ numba==0.60.0
178
+ numpy==1.26.4
179
+ nvidia-cublas-cu12==12.1.3.1
180
+ nvidia-cuda-cupti-cu12==12.1.105
181
+ nvidia-cuda-nvrtc-cu12==12.1.105
182
+ nvidia-cuda-runtime-cu12==12.1.105
183
+ nvidia-cudnn-cu12==9.1.0.70
184
+ nvidia-cufft-cu12==11.0.2.54
185
+ nvidia-curand-cu12==10.3.2.106
186
+ nvidia-cusolver-cu12==11.4.5.107
187
+ nvidia-cusparse-cu12==12.1.0.106
188
+ nvidia-nccl-cu12==2.20.5
189
+ nvidia-nvjitlink-cu12==12.6.68
190
+ nvidia-nvtx-cu12==12.1.105
191
+ omegaconf==2.3.0
192
+ onnx==1.16.2
193
+ onnxruntime-gpu @ file:///home/yinuo/tools/onnxruntime_gpu-1.17.0-cp310-cp310-manylinux_2_28_x86_64.whl#sha256=1f2a4e0468ac0bd8246996c3d5dbba92cbbaca874bcd7f9cee4e99ce6eb27f5b
194
+ opencv-contrib-python==4.10.0.84
195
+ opencv-python==4.10.0.84
196
+ opencv-python-headless==4.10.0.84
197
+ opt_einsum==3.4.0
198
+ orjson==3.10.7
199
+ packaging @ file:///home/conda/feedstock_root/build_artifacts/packaging_1718189413536/work
200
+ pandas==1.5.3
201
+ parso @ file:///home/conda/feedstock_root/build_artifacts/parso_1712320355065/work
202
+ pexpect @ file:///home/conda/feedstock_root/build_artifacts/pexpect_1706113125309/work
203
+ pfzy==0.3.4
204
+ pickleshare @ file:///home/conda/feedstock_root/build_artifacts/pickleshare_1602536217715/work
205
+ pillow==10.4.0
206
+ platformdirs @ file:///home/conda/feedstock_root/build_artifacts/platformdirs_1726613481435/work
207
+ pooch==1.8.2
208
+ preshed==3.0.9
209
+ prettytable==3.11.0
210
+ proglog==0.1.10
211
+ prompt_toolkit @ file:///home/conda/feedstock_root/build_artifacts/prompt-toolkit_1727341649933/work
212
+ protobuf==4.25.5
213
+ psutil @ file:///opt/conda/conda-bld/psutil_1656431268089/work
214
+ ptyprocess @ file:///home/conda/feedstock_root/build_artifacts/ptyprocess_1609419310487/work/dist/ptyprocess-0.7.0-py2.py3-none-any.whl
215
+ pure_eval @ file:///home/conda/feedstock_root/build_artifacts/pure_eval_1721585709575/work
216
+ pycparser==2.22
217
+ pycuda==2024.1.2
218
+ pydantic==2.9.2
219
+ pydantic_core==2.23.4
220
+ pydub==0.25.1
221
+ pyee==12.1.1
222
+ Pygments @ file:///home/conda/feedstock_root/build_artifacts/pygments_1714846767233/work
223
+ pykalman==0.9.7
224
+ pylibsrtp==0.10.0
225
+ PyMCubes==0.1.6
226
+ pynndescent==0.5.13
227
+ pyOpenSSL==24.3.0
228
+ pyparsing==3.1.4
229
+ pypinyin==0.53.0
230
+ pysbd==0.3.4
231
+ PySocks==1.7.1
232
+ python-crfsuite==0.9.10
233
+ python-dateutil @ file:///home/conda/feedstock_root/build_artifacts/python-dateutil_1709299778482/work
234
+ python-engineio==4.11.2
235
+ python-multipart==0.0.12
236
+ python-socketio==5.12.1
237
+ pytools==2024.1.14
238
+ pytz==2024.2
239
+ PyYAML==6.0.2
240
+ pyzmq @ file:///croot/pyzmq_1705605076900/work
241
+ redis==5.2.1
242
+ referencing==0.35.1
243
+ regex==2024.9.11
244
+ requests==2.32.3
245
+ requests-toolbelt==1.0.0
246
+ resampy==0.4.3
247
+ rich==13.8.1
248
+ rotary-embedding-torch==0.8.4
249
+ rpds-py==0.20.0
250
+ ruff==0.6.8
251
+ safehttpx==0.1.1
252
+ safetensors==0.4.5
253
+ scikit-image==0.24.0
254
+ scikit-learn==1.5.2
255
+ scipy==1.11.4
256
+ semantic-version==2.10.0
257
+ sentry-sdk==2.17.0
258
+ setproctitle==1.3.3
259
+ shellingham==1.5.4
260
+ shtab==1.7.1
261
+ simple-websocket==1.1.0
262
+ six @ file:///home/conda/feedstock_root/build_artifacts/six_1620240208055/work
263
+ smart-open==7.0.4
264
+ smmap==5.0.1
265
+ sniffio==1.3.1
266
+ sounddevice==0.5.0
267
+ soundfile==0.12.1
268
+ soupsieve==2.6
269
+ soxr==0.5.0.post1
270
+ spacy==3.7.5
271
+ spacy-legacy==3.0.12
272
+ spacy-loggers==1.0.5
273
+ srsly==2.4.8
274
+ srt==3.5.3
275
+ stack-data @ file:///home/conda/feedstock_root/build_artifacts/stack_data_1669632077133/work
276
+ starlette==0.41.2
277
+ SudachiDict-core==20240716
278
+ SudachiPy==0.6.8
279
+ sympy==1.13.3
280
+ tabulate==0.9.0
281
+ tb-nightly==2.19.0a20240930
282
+ tensorboard==2.18.0
283
+ tensorboard-data-server==0.7.2
284
+ tensorboardX==2.6.2.2
285
+ tensorrt @ file:///home/yinuo/tools/TensorRT-8.6.1.6/python/tensorrt-8.6.1-cp310-none-linux_x86_64.whl#sha256=2684b4772cb16088184266728a0668f5dac14e66f088c4ccff2096ccb222d74c
286
+ tensorrt-cu12==10.4.0
287
+ tensorrt-cu12-bindings==10.4.0
288
+ tensorrt-cu12-libs==10.4.0
289
+ thinc==8.2.5
290
+ threadpoolctl==3.5.0
291
+ tifffile==2024.9.20
292
+ tokenizers==0.20.0
293
+ tomli==2.0.1
294
+ tomlkit==0.12.0
295
+ torch==2.4.1
296
+ torch-ema==0.3
297
+ torchaudio==2.4.1
298
+ torchgeometry==0.1.2
299
+ torchvision==0.19.1
300
+ tornado @ file:///home/conda/feedstock_root/build_artifacts/tornado_1648827254365/work
301
+ tqdm==4.66.5
302
+ trainer==0.0.36
303
+ traitlets @ file:///home/conda/feedstock_root/build_artifacts/traitlets_1713535121073/work
304
+ transformers==4.45.1
305
+ trimesh==4.5.3
306
+ triton==3.0.0
307
+ TTS==0.22.0
308
+ typeguard==4.3.0
309
+ typer==0.12.5
310
+ typing_extensions @ file:///home/conda/feedstock_root/build_artifacts/typing_extensions_1717802530399/work
311
+ tyro==0.8.11
312
+ tzdata==2024.2
313
+ tzlocal==5.2
314
+ umap-learn==0.5.6
315
+ Unidecode==1.3.8
316
+ urllib3==2.2.3
317
+ uvicorn==0.30.6
318
+ vine==5.1.0
319
+ wandb==0.18.5
320
+ wasabi==1.1.3
321
+ wcwidth @ file:///home/conda/feedstock_root/build_artifacts/wcwidth_1704731205417/work
322
+ weasel==0.4.1
323
+ websockets==11.0.3
324
+ Werkzeug==3.0.4
325
+ widgetsnbextension==4.0.13
326
+ wrapt==1.16.0
327
+ wsproto==1.2.0
328
+ yacs==0.1.8
329
+ yapf==0.40.2
330
+ yarl==1.13.1
331
+ zipp==3.20.2
332
+ zope.event==5.0
333
+ zope.interface==7.2