torchaudio 2.7.1__cp311-cp311-win_amd64.whl → 2.9.0__cp311-cp311-win_amd64.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of torchaudio might be problematic. Click here for more details.
- torchaudio/__init__.py +184 -33
- torchaudio/_extension/__init__.py +1 -14
- torchaudio/_extension/utils.py +0 -47
- torchaudio/_internal/module_utils.py +68 -10
- torchaudio/_torchcodec.py +340 -0
- torchaudio/datasets/cmuarctic.py +1 -1
- torchaudio/datasets/utils.py +1 -1
- torchaudio/functional/__init__.py +6 -3
- torchaudio/functional/_alignment.py +1 -1
- torchaudio/functional/filtering.py +70 -55
- torchaudio/functional/functional.py +31 -61
- torchaudio/lib/_torchaudio.pyd +0 -0
- torchaudio/lib/libtorchaudio.pyd +0 -0
- torchaudio/models/decoder/__init__.py +19 -1
- torchaudio/models/decoder/_ctc_decoder.py +6 -6
- torchaudio/models/decoder/_cuda_ctc_decoder.py +1 -1
- torchaudio/models/squim/objective.py +2 -2
- torchaudio/pipelines/_source_separation_pipeline.py +1 -1
- torchaudio/pipelines/_squim_pipeline.py +2 -2
- torchaudio/pipelines/_tts/utils.py +3 -1
- torchaudio/pipelines/rnnt_pipeline.py +4 -4
- torchaudio/transforms/__init__.py +4 -1
- torchaudio/transforms/_transforms.py +4 -3
- torchaudio/utils/__init__.py +2 -9
- torchaudio/utils/download.py +1 -1
- torchaudio/version.py +2 -2
- {torchaudio-2.7.1.dist-info → torchaudio-2.9.0.dist-info}/METADATA +15 -7
- torchaudio-2.9.0.dist-info/RECORD +85 -0
- {torchaudio-2.7.1.dist-info → torchaudio-2.9.0.dist-info}/top_level.txt +0 -1
- torchaudio/_backend/__init__.py +0 -61
- torchaudio/_backend/backend.py +0 -53
- torchaudio/_backend/common.py +0 -52
- torchaudio/_backend/ffmpeg.py +0 -334
- torchaudio/_backend/soundfile.py +0 -54
- torchaudio/_backend/soundfile_backend.py +0 -457
- torchaudio/_backend/sox.py +0 -91
- torchaudio/_backend/utils.py +0 -317
- torchaudio/backend/__init__.py +0 -8
- torchaudio/backend/_no_backend.py +0 -25
- torchaudio/backend/_sox_io_backend.py +0 -294
- torchaudio/backend/common.py +0 -13
- torchaudio/backend/no_backend.py +0 -14
- torchaudio/backend/soundfile_backend.py +0 -14
- torchaudio/backend/sox_io_backend.py +0 -14
- torchaudio/io/__init__.py +0 -13
- torchaudio/io/_effector.py +0 -347
- torchaudio/io/_playback.py +0 -72
- torchaudio/kaldi_io.py +0 -144
- torchaudio/prototype/__init__.py +0 -0
- torchaudio/prototype/datasets/__init__.py +0 -4
- torchaudio/prototype/datasets/musan.py +0 -67
- torchaudio/prototype/functional/__init__.py +0 -26
- torchaudio/prototype/functional/_dsp.py +0 -433
- torchaudio/prototype/functional/_rir.py +0 -379
- torchaudio/prototype/functional/functional.py +0 -190
- torchaudio/prototype/models/__init__.py +0 -36
- torchaudio/prototype/models/_conformer_wav2vec2.py +0 -794
- torchaudio/prototype/models/_emformer_hubert.py +0 -333
- torchaudio/prototype/models/conv_emformer.py +0 -525
- torchaudio/prototype/models/hifi_gan.py +0 -336
- torchaudio/prototype/models/rnnt.py +0 -711
- torchaudio/prototype/models/rnnt_decoder.py +0 -399
- torchaudio/prototype/pipelines/__init__.py +0 -12
- torchaudio/prototype/pipelines/_vggish/__init__.py +0 -3
- torchaudio/prototype/pipelines/_vggish/_vggish_impl.py +0 -233
- torchaudio/prototype/pipelines/_vggish/_vggish_pipeline.py +0 -82
- torchaudio/prototype/pipelines/hifigan_pipeline.py +0 -228
- torchaudio/prototype/pipelines/rnnt_pipeline.py +0 -58
- torchaudio/prototype/transforms/__init__.py +0 -9
- torchaudio/prototype/transforms/_transforms.py +0 -456
- torchaudio/sox_effects/__init__.py +0 -10
- torchaudio/sox_effects/sox_effects.py +0 -272
- torchaudio/utils/ffmpeg_utils.py +0 -11
- torchaudio/utils/sox_utils.py +0 -99
- torchaudio-2.7.1.dist-info/RECORD +0 -144
- torio/__init__.py +0 -8
- torio/_extension/__init__.py +0 -13
- torio/_extension/utils.py +0 -147
- torio/io/__init__.py +0 -9
- torio/io/_streaming_media_decoder.py +0 -978
- torio/io/_streaming_media_encoder.py +0 -502
- torio/lib/__init__.py +0 -0
- torio/lib/_torio_ffmpeg4.pyd +0 -0
- torio/lib/_torio_ffmpeg5.pyd +0 -0
- torio/lib/_torio_ffmpeg6.pyd +0 -0
- torio/lib/libtorio_ffmpeg4.pyd +0 -0
- torio/lib/libtorio_ffmpeg5.pyd +0 -0
- torio/lib/libtorio_ffmpeg6.pyd +0 -0
- torio/utils/__init__.py +0 -4
- torio/utils/ffmpeg_utils.py +0 -247
- {torchaudio-2.7.1.dist-info → torchaudio-2.9.0.dist-info}/WHEEL +0 -0
- {torchaudio-2.7.1.dist-info → torchaudio-2.9.0.dist-info}/licenses/LICENSE +0 -0
torio/utils/ffmpeg_utils.py
DELETED
|
@@ -1,247 +0,0 @@
|
|
|
1
|
-
"""Module to change the configuration of FFmpeg libraries (such as libavformat).
|
|
2
|
-
|
|
3
|
-
It affects functionalities in :py:mod:`torio.io`.
|
|
4
|
-
"""
|
|
5
|
-
from typing import Dict, List, Tuple
|
|
6
|
-
|
|
7
|
-
import torio
|
|
8
|
-
|
|
9
|
-
ffmpeg_ext = torio._extension.lazy_import_ffmpeg_ext()
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
def get_versions() -> Dict[str, Tuple[int]]:
|
|
13
|
-
"""Get the versions of FFmpeg libraries
|
|
14
|
-
|
|
15
|
-
Returns:
|
|
16
|
-
dict: mapping from library names to version string,
|
|
17
|
-
i.e. `"libavutil": (56, 22, 100)`.
|
|
18
|
-
"""
|
|
19
|
-
return ffmpeg_ext.get_versions()
|
|
20
|
-
|
|
21
|
-
|
|
22
|
-
def get_log_level() -> int:
|
|
23
|
-
"""Get the log level of FFmpeg.
|
|
24
|
-
|
|
25
|
-
See :py:func:`set_log_level` for the detail.
|
|
26
|
-
"""
|
|
27
|
-
return ffmpeg_ext.get_log_level()
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
def set_log_level(level: int):
|
|
31
|
-
"""Set the log level of FFmpeg (libavformat etc)
|
|
32
|
-
|
|
33
|
-
Arguments:
|
|
34
|
-
level (int): Log level. The larger, the more verbose.
|
|
35
|
-
|
|
36
|
-
The following values are common values, the corresponding ``ffmpeg``'s
|
|
37
|
-
``-loglevel`` option value and desription.
|
|
38
|
-
|
|
39
|
-
* ``-8`` (``quiet``):
|
|
40
|
-
Print no output.
|
|
41
|
-
* ``0`` (``panic``):
|
|
42
|
-
Something went really wrong and we will crash now.
|
|
43
|
-
* ``8`` (``fatal``):
|
|
44
|
-
Something went wrong and recovery is not possible.
|
|
45
|
-
For example, no header was found for a format which depends
|
|
46
|
-
on headers or an illegal combination of parameters is used.
|
|
47
|
-
* ``16`` (``error``):
|
|
48
|
-
Something went wrong and cannot losslessly be recovered.
|
|
49
|
-
However, not all future data is affected.
|
|
50
|
-
* ``24`` (``warning``):
|
|
51
|
-
Something somehow does not look correct.
|
|
52
|
-
This may or may not lead to problems.
|
|
53
|
-
* ``32`` (``info``):
|
|
54
|
-
Standard information.
|
|
55
|
-
* ``40`` (``verbose``):
|
|
56
|
-
Detailed information.
|
|
57
|
-
* ``48`` (``debug``):
|
|
58
|
-
Stuff which is only useful for libav* developers.
|
|
59
|
-
* ``56`` (``trace``):
|
|
60
|
-
Extremely verbose debugging, useful for libav* development.
|
|
61
|
-
|
|
62
|
-
"""
|
|
63
|
-
ffmpeg_ext.set_log_level(level)
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
def get_demuxers() -> Dict[str, str]:
|
|
67
|
-
"""Get the available demuxers.
|
|
68
|
-
|
|
69
|
-
Returns:
|
|
70
|
-
Dict[str, str]: Mapping from demuxer (format) short name to long name.
|
|
71
|
-
|
|
72
|
-
Example
|
|
73
|
-
>>> for k, v in get_demuxers().items():
|
|
74
|
-
>>> print(f"{k}: {v}")
|
|
75
|
-
... aa: Audible AA format files
|
|
76
|
-
... aac: raw ADTS AAC (Advanced Audio Coding)
|
|
77
|
-
... aax: CRI AAX
|
|
78
|
-
... ac3: raw AC-3
|
|
79
|
-
"""
|
|
80
|
-
return ffmpeg_ext.get_demuxers()
|
|
81
|
-
|
|
82
|
-
|
|
83
|
-
def get_muxers() -> Dict[str, str]:
|
|
84
|
-
"""Get the available muxers.
|
|
85
|
-
|
|
86
|
-
Returns:
|
|
87
|
-
Dict[str, str]: Mapping from muxer (format) short name to long name.
|
|
88
|
-
|
|
89
|
-
Example
|
|
90
|
-
>>> for k, v in get_muxers().items():
|
|
91
|
-
>>> print(f"{k}: {v}")
|
|
92
|
-
... a64: a64 - video for Commodore 64
|
|
93
|
-
... ac3: raw AC-3
|
|
94
|
-
... adts: ADTS AAC (Advanced Audio Coding)
|
|
95
|
-
... adx: CRI ADX
|
|
96
|
-
... aiff: Audio IFF
|
|
97
|
-
"""
|
|
98
|
-
return ffmpeg_ext.get_muxers()
|
|
99
|
-
|
|
100
|
-
|
|
101
|
-
def get_audio_decoders() -> Dict[str, str]:
|
|
102
|
-
"""Get the available audio decoders.
|
|
103
|
-
|
|
104
|
-
Returns:
|
|
105
|
-
Dict[str, str]: Mapping from decoder short name to long name.
|
|
106
|
-
|
|
107
|
-
Example
|
|
108
|
-
>>> for k, v in get_audio_decoders().items():
|
|
109
|
-
>>> print(f"{k}: {v}")
|
|
110
|
-
... a64: a64 - video for Commodore 64
|
|
111
|
-
... ac3: raw AC-3
|
|
112
|
-
... adts: ADTS AAC (Advanced Audio Coding)
|
|
113
|
-
... adx: CRI ADX
|
|
114
|
-
... aiff: Audio IFF
|
|
115
|
-
"""
|
|
116
|
-
return ffmpeg_ext.get_audio_decoders()
|
|
117
|
-
|
|
118
|
-
|
|
119
|
-
def get_audio_encoders() -> Dict[str, str]:
|
|
120
|
-
"""Get the available audio encoders.
|
|
121
|
-
|
|
122
|
-
Returns:
|
|
123
|
-
Dict[str, str]: Mapping from encoder short name to long name.
|
|
124
|
-
|
|
125
|
-
Example
|
|
126
|
-
>>> for k, v in get_audio_encoders().items():
|
|
127
|
-
>>> print(f"{k}: {v}")
|
|
128
|
-
... comfortnoise: RFC 3389 comfort noise generator
|
|
129
|
-
... s302m: SMPTE 302M
|
|
130
|
-
... aac: AAC (Advanced Audio Coding)
|
|
131
|
-
... ac3: ATSC A/52A (AC-3)
|
|
132
|
-
... ac3_fixed: ATSC A/52A (AC-3)
|
|
133
|
-
... alac: ALAC (Apple Lossless Audio Codec)
|
|
134
|
-
"""
|
|
135
|
-
return ffmpeg_ext.get_audio_encoders()
|
|
136
|
-
|
|
137
|
-
|
|
138
|
-
def get_video_decoders() -> Dict[str, str]:
|
|
139
|
-
"""Get the available video decoders.
|
|
140
|
-
|
|
141
|
-
Returns:
|
|
142
|
-
Dict[str, str]: Mapping from decoder short name to long name.
|
|
143
|
-
|
|
144
|
-
Example
|
|
145
|
-
>>> for k, v in get_video_decoders().items():
|
|
146
|
-
>>> print(f"{k}: {v}")
|
|
147
|
-
... aasc: Autodesk RLE
|
|
148
|
-
... aic: Apple Intermediate Codec
|
|
149
|
-
... alias_pix: Alias/Wavefront PIX image
|
|
150
|
-
... agm: Amuse Graphics Movie
|
|
151
|
-
... amv: AMV Video
|
|
152
|
-
... anm: Deluxe Paint Animation
|
|
153
|
-
"""
|
|
154
|
-
return ffmpeg_ext.get_video_decoders()
|
|
155
|
-
|
|
156
|
-
|
|
157
|
-
def get_video_encoders() -> Dict[str, str]:
|
|
158
|
-
"""Get the available video encoders.
|
|
159
|
-
|
|
160
|
-
Returns:
|
|
161
|
-
Dict[str, str]: Mapping from encoder short name to long name.
|
|
162
|
-
|
|
163
|
-
Example
|
|
164
|
-
>>> for k, v in get_audio_encoders().items():
|
|
165
|
-
>>> print(f"{k}: {v}")
|
|
166
|
-
... a64multi: Multicolor charset for Commodore 64
|
|
167
|
-
... a64multi5: Multicolor charset for Commodore 64, extended with 5th color (colram)
|
|
168
|
-
... alias_pix: Alias/Wavefront PIX image
|
|
169
|
-
... amv: AMV Video
|
|
170
|
-
... apng: APNG (Animated Portable Network Graphics) image
|
|
171
|
-
... asv1: ASUS V1
|
|
172
|
-
... asv2: ASUS V2
|
|
173
|
-
"""
|
|
174
|
-
return ffmpeg_ext.get_video_encoders()
|
|
175
|
-
|
|
176
|
-
|
|
177
|
-
def get_input_devices() -> Dict[str, str]:
|
|
178
|
-
"""Get the available input devices.
|
|
179
|
-
|
|
180
|
-
Returns:
|
|
181
|
-
Dict[str, str]: Mapping from device short name to long name.
|
|
182
|
-
|
|
183
|
-
Example
|
|
184
|
-
>>> for k, v in get_input_devices().items():
|
|
185
|
-
>>> print(f"{k}: {v}")
|
|
186
|
-
... avfoundation: AVFoundation input device
|
|
187
|
-
... lavfi: Libavfilter virtual input device
|
|
188
|
-
"""
|
|
189
|
-
return ffmpeg_ext.get_input_devices()
|
|
190
|
-
|
|
191
|
-
|
|
192
|
-
def get_output_devices() -> Dict[str, str]:
|
|
193
|
-
"""Get the available output devices.
|
|
194
|
-
|
|
195
|
-
Returns:
|
|
196
|
-
Dict[str, str]: Mapping from device short name to long name.
|
|
197
|
-
|
|
198
|
-
Example
|
|
199
|
-
>>> for k, v in get_output_devices().items():
|
|
200
|
-
>>> print(f"{k}: {v}")
|
|
201
|
-
... audiotoolbox: AudioToolbox output device
|
|
202
|
-
"""
|
|
203
|
-
return ffmpeg_ext.get_output_devices()
|
|
204
|
-
|
|
205
|
-
|
|
206
|
-
def get_input_protocols() -> List[str]:
|
|
207
|
-
"""Get the supported input protocols.
|
|
208
|
-
|
|
209
|
-
Returns:
|
|
210
|
-
List[str]: The names of supported input protocols
|
|
211
|
-
|
|
212
|
-
Example
|
|
213
|
-
>>> print(get_input_protocols())
|
|
214
|
-
... ['file', 'ftp', 'hls', 'http','https', 'pipe', 'rtmp', 'tcp', 'tls', 'udp', 'unix']
|
|
215
|
-
"""
|
|
216
|
-
return ffmpeg_ext.get_input_protocols()
|
|
217
|
-
|
|
218
|
-
|
|
219
|
-
def get_output_protocols() -> List[str]:
|
|
220
|
-
"""Get the supported output protocols.
|
|
221
|
-
|
|
222
|
-
Returns:
|
|
223
|
-
list of str: The names of supported output protocols
|
|
224
|
-
|
|
225
|
-
Example
|
|
226
|
-
>>> print(get_output_protocols())
|
|
227
|
-
... ['file', 'ftp', 'http', 'https', 'md5', 'pipe', 'prompeg', 'rtmp', 'tee', 'tcp', 'tls', 'udp', 'unix']
|
|
228
|
-
"""
|
|
229
|
-
return ffmpeg_ext.get_output_protocols()
|
|
230
|
-
|
|
231
|
-
|
|
232
|
-
def get_build_config() -> str:
|
|
233
|
-
"""Get the FFmpeg build configuration
|
|
234
|
-
|
|
235
|
-
Returns:
|
|
236
|
-
str: Build configuration string.
|
|
237
|
-
|
|
238
|
-
Example
|
|
239
|
-
>>> print(get_build_config())
|
|
240
|
-
--prefix=/Users/runner/miniforge3 --cc=arm64-apple-darwin20.0.0-clang --enable-gpl --enable-hardcoded-tables --enable-libfreetype --enable-libopenh264 --enable-neon --enable-libx264 --enable-libx265 --enable-libaom --enable-libsvtav1 --enable-libxml2 --enable-libvpx --enable-pic --enable-pthreads --enable-shared --disable-static --enable-version3 --enable-zlib --enable-libmp3lame --pkg-config=/Users/runner/miniforge3/conda-bld/ffmpeg_1646229390493/_build_env/bin/pkg-config --enable-cross-compile --arch=arm64 --target-os=darwin --cross-prefix=arm64-apple-darwin20.0.0- --host-cc=/Users/runner/miniforge3/conda-bld/ffmpeg_1646229390493/_build_env/bin/x86_64-apple-darwin13.4.0-clang # noqa
|
|
241
|
-
"""
|
|
242
|
-
return ffmpeg_ext.get_build_config()
|
|
243
|
-
|
|
244
|
-
|
|
245
|
-
def clear_cuda_context_cache():
|
|
246
|
-
"""Clear the CUDA context used by CUDA Hardware accelerated video decoding"""
|
|
247
|
-
ffmpeg_ext.clear_cuda_context_cache()
|
|
File without changes
|
|
File without changes
|