diff --git a/2.3 b/2.3 new file mode 120000 index 00000000000..cc6612c36e0 --- /dev/null +++ b/2.3 @@ -0,0 +1 @@ +2.3.0 \ No newline at end of file diff --git a/main/.buildinfo b/main/.buildinfo index 45cd3c14c29..da3585f1402 100644 --- a/main/.buildinfo +++ b/main/.buildinfo @@ -1,4 +1,4 @@ # Sphinx build info version 1 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done. -config: 420e3618b6a64cbffa0728122285af3f +config: cee05160870b3b8da75ca1f9c2e188d6 tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/main/_images/sphx_glr_audio_resampling_tutorial_013.png b/main/_images/sphx_glr_audio_resampling_tutorial_013.png index 1316444f629..a1330b755d7 100644 Binary files a/main/_images/sphx_glr_audio_resampling_tutorial_013.png and b/main/_images/sphx_glr_audio_resampling_tutorial_013.png differ diff --git a/main/_images/sphx_glr_audio_resampling_tutorial_014.png b/main/_images/sphx_glr_audio_resampling_tutorial_014.png index 8560084f7a1..b20948685ef 100644 Binary files a/main/_images/sphx_glr_audio_resampling_tutorial_014.png and b/main/_images/sphx_glr_audio_resampling_tutorial_014.png differ diff --git a/main/_images/sphx_glr_audio_resampling_tutorial_015.png b/main/_images/sphx_glr_audio_resampling_tutorial_015.png index cbd95628331..561199a066e 100644 Binary files a/main/_images/sphx_glr_audio_resampling_tutorial_015.png and b/main/_images/sphx_glr_audio_resampling_tutorial_015.png differ diff --git a/main/_images/sphx_glr_audio_resampling_tutorial_016.png b/main/_images/sphx_glr_audio_resampling_tutorial_016.png index fff647151f0..c84f468572f 100644 Binary files a/main/_images/sphx_glr_audio_resampling_tutorial_016.png and b/main/_images/sphx_glr_audio_resampling_tutorial_016.png differ diff --git a/main/_images/sphx_glr_nvdec_tutorial_004.png b/main/_images/sphx_glr_nvdec_tutorial_004.png index d8ac027c7be..aea23f20283 100644 Binary files a/main/_images/sphx_glr_nvdec_tutorial_004.png and b/main/_images/sphx_glr_nvdec_tutorial_004.png differ diff --git a/main/_images/sphx_glr_nvdec_tutorial_005.png b/main/_images/sphx_glr_nvdec_tutorial_005.png index 36f891d144d..7916b9d05cb 100644 Binary files a/main/_images/sphx_glr_nvdec_tutorial_005.png and b/main/_images/sphx_glr_nvdec_tutorial_005.png differ diff --git a/main/_images/sphx_glr_nvenc_tutorial_001.png b/main/_images/sphx_glr_nvenc_tutorial_001.png index 373b73d0dc8..0720b425927 100644 Binary files a/main/_images/sphx_glr_nvenc_tutorial_001.png and b/main/_images/sphx_glr_nvenc_tutorial_001.png differ diff --git a/main/_images/sphx_glr_nvenc_tutorial_thumb.png b/main/_images/sphx_glr_nvenc_tutorial_thumb.png index d7fe32e7562..258f3f5aba3 100644 Binary files a/main/_images/sphx_glr_nvenc_tutorial_thumb.png and b/main/_images/sphx_glr_nvenc_tutorial_thumb.png differ diff --git a/main/_modules/index.html b/main/_modules/index.html index 355b7acd6e5..b3d9d3e831a 100644 --- a/main/_modules/index.html +++ b/main/_modules/index.html @@ -9,7 +9,7 @@ -
All datasets are subclasses of torch.utils.data.Dataset
+
All datasets are subclasses of torch.utils.data.Dataset
and have __getitem__
and __len__
methods implemented.
Hence, they can all be passed to a torch.utils.data.DataLoader
-which can load multiple samples parallelly using torch.multiprocessing
workers.
+
Hence, they can all be passed to a torch.utils.data.DataLoader
+which can load multiple samples parallelly using torch.multiprocessing
workers.
For example:
yesno_data = torchaudio.datasets.YESNO('.', download=True)
data_loader = torch.utils.data.DataLoader(
diff --git a/main/feature_classifications.html b/main/feature_classifications.html
index c88bf5205bf..e62c08edfa1 100644
--- a/main/feature_classifications.html
+++ b/main/feature_classifications.html
@@ -10,7 +10,7 @@
- Feature Classifications — Torchaudio 2.2.0.dev20240424 documentation
+ Feature Classifications — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
diff --git a/main/functional.html b/main/functional.html
index 7daca6597f8..02bbb35d9d4 100644
--- a/main/functional.html
+++ b/main/functional.html
@@ -10,7 +10,7 @@
- torchaudio.functional — Torchaudio 2.2.0.dev20240424 documentation
+ torchaudio.functional — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
diff --git a/main/generated/torchaudio.compliance.kaldi.fbank.html b/main/generated/torchaudio.compliance.kaldi.fbank.html
index e856e830345..a724e643765 100644
--- a/main/generated/torchaudio.compliance.kaldi.fbank.html
+++ b/main/generated/torchaudio.compliance.kaldi.fbank.html
@@ -10,7 +10,7 @@
- torchaudio.compliance.kaldi.fbank — Torchaudio 2.2.0.dev20240424 documentation
+ torchaudio.compliance.kaldi.fbank — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -440,7 +440,7 @@
torchaudio.compliance.kaldi.fbankĀ¶
-
-torchaudio.compliance.kaldi.fbank(waveform: Tensor, blackman_coeff: float = 0.42, channel: int = -1, dither: float = 0.0, energy_floor: float = 1.0, frame_length: float = 25.0, frame_shift: float = 10.0, high_freq: float = 0.0, htk_compat: bool = False, low_freq: float = 20.0, min_duration: float = 0.0, num_mel_bins: int = 23, preemphasis_coefficient: float = 0.97, raw_energy: bool = True, remove_dc_offset: bool = True, round_to_power_of_two: bool = True, sample_frequency: float = 16000.0, snip_edges: bool = True, subtract_mean: bool = False, use_energy: bool = False, use_log_fbank: bool = True, use_power: bool = True, vtln_high: float = -500.0, vtln_low: float = 100.0, vtln_warp: float = 1.0, window_type: str = 'povey') → Tensor[source]Ā¶
+torchaudio.compliance.kaldi.fbank(waveform: Tensor, blackman_coeff: float = 0.42, channel: int = -1, dither: float = 0.0, energy_floor: float = 1.0, frame_length: float = 25.0, frame_shift: float = 10.0, high_freq: float = 0.0, htk_compat: bool = False, low_freq: float = 20.0, min_duration: float = 0.0, num_mel_bins: int = 23, preemphasis_coefficient: float = 0.97, raw_energy: bool = True, remove_dc_offset: bool = True, round_to_power_of_two: bool = True, sample_frequency: float = 16000.0, snip_edges: bool = True, subtract_mean: bool = False, use_energy: bool = False, use_log_fbank: bool = True, use_power: bool = True, vtln_high: float = -500.0, vtln_low: float = 100.0, vtln_warp: float = 1.0, window_type: str = 'povey') → Tensor[source]Ā¶
Create a fbank from a raw audio signal. This matches the input/output of Kaldiās
compute-fbank-feats.
diff --git a/main/generated/torchaudio.compliance.kaldi.mfcc.html b/main/generated/torchaudio.compliance.kaldi.mfcc.html
index c0a838b820c..49626d4aa00 100644
--- a/main/generated/torchaudio.compliance.kaldi.mfcc.html
+++ b/main/generated/torchaudio.compliance.kaldi.mfcc.html
@@ -10,7 +10,7 @@
- torchaudio.compliance.kaldi.mfcc — Torchaudio 2.2.0.dev20240424 documentation
+ torchaudio.compliance.kaldi.mfcc — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -440,7 +440,7 @@
torchaudio.compliance.kaldi.mfccĀ¶
-
-torchaudio.compliance.kaldi.mfcc(waveform: Tensor, blackman_coeff: float = 0.42, cepstral_lifter: float = 22.0, channel: int = -1, dither: float = 0.0, energy_floor: float = 1.0, frame_length: float = 25.0, frame_shift: float = 10.0, high_freq: float = 0.0, htk_compat: bool = False, low_freq: float = 20.0, num_ceps: int = 13, min_duration: float = 0.0, num_mel_bins: int = 23, preemphasis_coefficient: float = 0.97, raw_energy: bool = True, remove_dc_offset: bool = True, round_to_power_of_two: bool = True, sample_frequency: float = 16000.0, snip_edges: bool = True, subtract_mean: bool = False, use_energy: bool = False, vtln_high: float = -500.0, vtln_low: float = 100.0, vtln_warp: float = 1.0, window_type: str = 'povey') → Tensor[source]Ā¶
+torchaudio.compliance.kaldi.mfcc(waveform: Tensor, blackman_coeff: float = 0.42, cepstral_lifter: float = 22.0, channel: int = -1, dither: float = 0.0, energy_floor: float = 1.0, frame_length: float = 25.0, frame_shift: float = 10.0, high_freq: float = 0.0, htk_compat: bool = False, low_freq: float = 20.0, num_ceps: int = 13, min_duration: float = 0.0, num_mel_bins: int = 23, preemphasis_coefficient: float = 0.97, raw_energy: bool = True, remove_dc_offset: bool = True, round_to_power_of_two: bool = True, sample_frequency: float = 16000.0, snip_edges: bool = True, subtract_mean: bool = False, use_energy: bool = False, vtln_high: float = -500.0, vtln_low: float = 100.0, vtln_warp: float = 1.0, window_type: str = 'povey') → Tensor[source]Ā¶
Create a mfcc from a raw audio signal. This matches the input/output of Kaldiās
compute-mfcc-feats.
diff --git a/main/generated/torchaudio.compliance.kaldi.spectrogram.html b/main/generated/torchaudio.compliance.kaldi.spectrogram.html
index 23a0f803021..0fd3e6d6be4 100644
--- a/main/generated/torchaudio.compliance.kaldi.spectrogram.html
+++ b/main/generated/torchaudio.compliance.kaldi.spectrogram.html
@@ -10,7 +10,7 @@
- torchaudio.compliance.kaldi.spectrogram — Torchaudio 2.2.0.dev20240424 documentation
+ torchaudio.compliance.kaldi.spectrogram — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -440,7 +440,7 @@
torchaudio.compliance.kaldi.spectrogramĀ¶
-
-torchaudio.compliance.kaldi.spectrogram(waveform: Tensor, blackman_coeff: float = 0.42, channel: int = -1, dither: float = 0.0, energy_floor: float = 1.0, frame_length: float = 25.0, frame_shift: float = 10.0, min_duration: float = 0.0, preemphasis_coefficient: float = 0.97, raw_energy: bool = True, remove_dc_offset: bool = True, round_to_power_of_two: bool = True, sample_frequency: float = 16000.0, snip_edges: bool = True, subtract_mean: bool = False, window_type: str = 'povey') → Tensor[source]Ā¶
+torchaudio.compliance.kaldi.spectrogram(waveform: Tensor, blackman_coeff: float = 0.42, channel: int = -1, dither: float = 0.0, energy_floor: float = 1.0, frame_length: float = 25.0, frame_shift: float = 10.0, min_duration: float = 0.0, preemphasis_coefficient: float = 0.97, raw_energy: bool = True, remove_dc_offset: bool = True, round_to_power_of_two: bool = True, sample_frequency: float = 16000.0, snip_edges: bool = True, subtract_mean: bool = False, window_type: str = 'povey') → Tensor[source]Ā¶
Create a spectrogram from a raw audio signal. This matches the input/output of Kaldiās
compute-spectrogram-feats.
diff --git a/main/generated/torchaudio.datasets.CMUARCTIC.html b/main/generated/torchaudio.datasets.CMUARCTIC.html
index 7e034e7820a..7cebb4676db 100644
--- a/main/generated/torchaudio.datasets.CMUARCTIC.html
+++ b/main/generated/torchaudio.datasets.CMUARCTIC.html
@@ -10,7 +10,7 @@
- CMUARCTIC — Torchaudio 2.2.0.dev20240424 documentation
+ CMUARCTIC — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -463,7 +463,7 @@ __getitem__
-
-CMUARCTIC.__getitem__(n: int) → Tuple[Tensor, int, str, str][source]Ā¶
+CMUARCTIC.__getitem__(n: int) → Tuple[Tensor, int, str, str][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.CMUDict.html b/main/generated/torchaudio.datasets.CMUDict.html
index 620895e23c4..51dbba0e458 100644
--- a/main/generated/torchaudio.datasets.CMUDict.html
+++ b/main/generated/torchaudio.datasets.CMUDict.html
@@ -10,7 +10,7 @@
- CMUDict — Torchaudio 2.2.0.dev20240424 documentation
+ CMUDict — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
diff --git a/main/generated/torchaudio.datasets.COMMONVOICE.html b/main/generated/torchaudio.datasets.COMMONVOICE.html
index 5d80cbddd7c..4f5bb8113b0 100644
--- a/main/generated/torchaudio.datasets.COMMONVOICE.html
+++ b/main/generated/torchaudio.datasets.COMMONVOICE.html
@@ -10,7 +10,7 @@
- COMMONVOICE — Torchaudio 2.2.0.dev20240424 documentation
+ COMMONVOICE — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -460,7 +460,7 @@ __getitem__
-
-COMMONVOICE.__getitem__(n: int) → Tuple[Tensor, int, Dict[str, str]][source]Ā¶
+COMMONVOICE.__getitem__(n: int) → Tuple[Tensor, int, Dict[str, str]][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.DR_VCTK.html b/main/generated/torchaudio.datasets.DR_VCTK.html
index d5c894f0037..70b55c21904 100644
--- a/main/generated/torchaudio.datasets.DR_VCTK.html
+++ b/main/generated/torchaudio.datasets.DR_VCTK.html
@@ -10,7 +10,7 @@
- DR_VCTK — Torchaudio 2.2.0.dev20240424 documentation
+ DR_VCTK — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -460,7 +460,7 @@ __getitem__
-
-DR_VCTK.__getitem__(n: int) → Tuple[Tensor, int, Tensor, int, str, str, str, int][source]Ā¶
+DR_VCTK.__getitem__(n: int) → Tuple[Tensor, int, Tensor, int, str, str, str, int][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.FluentSpeechCommands.html b/main/generated/torchaudio.datasets.FluentSpeechCommands.html
index e93cd1ac6f7..2f842688e12 100644
--- a/main/generated/torchaudio.datasets.FluentSpeechCommands.html
+++ b/main/generated/torchaudio.datasets.FluentSpeechCommands.html
@@ -10,7 +10,7 @@
- FluentSpeechCommands — Torchaudio 2.2.0.dev20240424 documentation
+ FluentSpeechCommands — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -459,7 +459,7 @@ __getitem__
-
-FluentSpeechCommands.__getitem__(n: int) → Tuple[Tensor, int, str, int, str, str, str, str][source]Ā¶
+FluentSpeechCommands.__getitem__(n: int) → Tuple[Tensor, int, str, int, str, str, str, str][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.GTZAN.html b/main/generated/torchaudio.datasets.GTZAN.html
index 9946469d088..393eceddd77 100644
--- a/main/generated/torchaudio.datasets.GTZAN.html
+++ b/main/generated/torchaudio.datasets.GTZAN.html
@@ -10,7 +10,7 @@
- GTZAN — Torchaudio 2.2.0.dev20240424 documentation
+ GTZAN — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -473,7 +473,7 @@ __getitem__
-
-GTZAN.__getitem__(n: int) → Tuple[Tensor, int, str][source]Ā¶
+GTZAN.__getitem__(n: int) → Tuple[Tensor, int, str][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.IEMOCAP.html b/main/generated/torchaudio.datasets.IEMOCAP.html
index e82d45581d7..ec63dc35b54 100644
--- a/main/generated/torchaudio.datasets.IEMOCAP.html
+++ b/main/generated/torchaudio.datasets.IEMOCAP.html
@@ -10,7 +10,7 @@
- IEMOCAP — Torchaudio 2.2.0.dev20240424 documentation
+ IEMOCAP — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -460,7 +460,7 @@ __getitem__
-
-IEMOCAP.__getitem__(n: int) → Tuple[Tensor, int, str, str, str][source]Ā¶
+IEMOCAP.__getitem__(n: int) → Tuple[Tensor, int, str, str, str][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.LIBRISPEECH.html b/main/generated/torchaudio.datasets.LIBRISPEECH.html
index f985e83f2e2..208ca1b510b 100644
--- a/main/generated/torchaudio.datasets.LIBRISPEECH.html
+++ b/main/generated/torchaudio.datasets.LIBRISPEECH.html
@@ -10,7 +10,7 @@
- LIBRISPEECH — Torchaudio 2.2.0.dev20240424 documentation
+ LIBRISPEECH — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -463,7 +463,7 @@ __getitem__
-
-LIBRISPEECH.__getitem__(n: int) → Tuple[Tensor, int, str, int, int, int][source]Ā¶
+LIBRISPEECH.__getitem__(n: int) → Tuple[Tensor, int, str, int, int, int][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.LIBRITTS.html b/main/generated/torchaudio.datasets.LIBRITTS.html
index b3d00ecc209..d63b403e141 100644
--- a/main/generated/torchaudio.datasets.LIBRITTS.html
+++ b/main/generated/torchaudio.datasets.LIBRITTS.html
@@ -10,7 +10,7 @@
- LIBRITTS — Torchaudio 2.2.0.dev20240424 documentation
+ LIBRITTS — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -463,7 +463,7 @@ __getitem__
-
-LIBRITTS.__getitem__(n: int) → Tuple[Tensor, int, str, str, int, int, str][source]Ā¶
+LIBRITTS.__getitem__(n: int) → Tuple[Tensor, int, str, str, int, int, str][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.LJSPEECH.html b/main/generated/torchaudio.datasets.LJSPEECH.html
index ef2f07cb83e..d1c2239e282 100644
--- a/main/generated/torchaudio.datasets.LJSPEECH.html
+++ b/main/generated/torchaudio.datasets.LJSPEECH.html
@@ -10,7 +10,7 @@
- LJSPEECH — Torchaudio 2.2.0.dev20240424 documentation
+ LJSPEECH — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -460,7 +460,7 @@ __getitem__
-
-LJSPEECH.__getitem__(n: int) → Tuple[Tensor, int, str, str][source]Ā¶
+LJSPEECH.__getitem__(n: int) → Tuple[Tensor, int, str, str][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.LibriLightLimited.html b/main/generated/torchaudio.datasets.LibriLightLimited.html
index 4ccdcfb4929..28b95e08694 100644
--- a/main/generated/torchaudio.datasets.LibriLightLimited.html
+++ b/main/generated/torchaudio.datasets.LibriLightLimited.html
@@ -10,7 +10,7 @@
- LibriLightLimited — Torchaudio 2.2.0.dev20240424 documentation
+ LibriLightLimited — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -460,7 +460,7 @@ __getitem__
-
-LibriLightLimited.__getitem__(n: int) → Tuple[Tensor, int, str, int, int, int][source]Ā¶
+LibriLightLimited.__getitem__(n: int) → Tuple[Tensor, int, str, int, int, int][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.LibriMix.html b/main/generated/torchaudio.datasets.LibriMix.html
index 20b90838373..cd757964ced 100644
--- a/main/generated/torchaudio.datasets.LibriMix.html
+++ b/main/generated/torchaudio.datasets.LibriMix.html
@@ -10,7 +10,7 @@
- LibriMix — Torchaudio 2.2.0.dev20240424 documentation
+ LibriMix — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -477,7 +477,7 @@ __getitem__
-
-LibriMix.__getitem__(key: int) → Tuple[int, Tensor, List[Tensor]][source]Ā¶
+LibriMix.__getitem__(key: int) → Tuple[int, Tensor, List[Tensor]][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.MUSDB_HQ.html b/main/generated/torchaudio.datasets.MUSDB_HQ.html
index 6403af6e1b2..b64604cac18 100644
--- a/main/generated/torchaudio.datasets.MUSDB_HQ.html
+++ b/main/generated/torchaudio.datasets.MUSDB_HQ.html
@@ -10,7 +10,7 @@
- MUSDB_HQ — Torchaudio 2.2.0.dev20240424 documentation
+ MUSDB_HQ — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -466,7 +466,7 @@ __getitem__
-
-MUSDB_HQ.__getitem__(n: int) → Tuple[Tensor, int, int, str][source]Ā¶
+MUSDB_HQ.__getitem__(n: int) → Tuple[Tensor, int, int, str][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.QUESST14.html b/main/generated/torchaudio.datasets.QUESST14.html
index fa76d142104..7e7de501772 100644
--- a/main/generated/torchaudio.datasets.QUESST14.html
+++ b/main/generated/torchaudio.datasets.QUESST14.html
@@ -10,7 +10,7 @@
- QUESST14 — Torchaudio 2.2.0.dev20240424 documentation
+ QUESST14 — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -462,7 +462,7 @@ __getitem__
-
-QUESST14.__getitem__(n: int) → Tuple[Tensor, int, str][source]Ā¶
+QUESST14.__getitem__(n: int) → Tuple[Tensor, int, str][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.SPEECHCOMMANDS.html b/main/generated/torchaudio.datasets.SPEECHCOMMANDS.html
index db6dc3cf0f0..b533d04a611 100644
--- a/main/generated/torchaudio.datasets.SPEECHCOMMANDS.html
+++ b/main/generated/torchaudio.datasets.SPEECHCOMMANDS.html
@@ -10,7 +10,7 @@
- SPEECHCOMMANDS — Torchaudio 2.2.0.dev20240424 documentation
+ SPEECHCOMMANDS — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -468,7 +468,7 @@ __getitem__
-
-SPEECHCOMMANDS.__getitem__(n: int) → Tuple[Tensor, int, str, str, int][source]Ā¶
+SPEECHCOMMANDS.__getitem__(n: int) → Tuple[Tensor, int, str, str, int][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.Snips.html b/main/generated/torchaudio.datasets.Snips.html
index 9451dd7fc40..53846b31e0d 100644
--- a/main/generated/torchaudio.datasets.Snips.html
+++ b/main/generated/torchaudio.datasets.Snips.html
@@ -10,7 +10,7 @@
- Snips — Torchaudio 2.2.0.dev20240424 documentation
+ Snips — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -461,7 +461,7 @@ __getitem__
-
-Snips.__getitem__(n: int) → Tuple[Tensor, int, str, str, str][source]Ā¶
+Snips.__getitem__(n: int) → Tuple[Tensor, int, str, str, str][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.TEDLIUM.html b/main/generated/torchaudio.datasets.TEDLIUM.html
index 89da6aa6aa5..cb6f4f820e9 100644
--- a/main/generated/torchaudio.datasets.TEDLIUM.html
+++ b/main/generated/torchaudio.datasets.TEDLIUM.html
@@ -10,7 +10,7 @@
- TEDLIUM — Torchaudio 2.2.0.dev20240424 documentation
+ TEDLIUM — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -486,7 +486,7 @@ __getitem__
-
-TEDLIUM.__getitem__(n: int) → Tuple[Tensor, int, str, int, int, int][source]Ā¶
+TEDLIUM.__getitem__(n: int) → Tuple[Tensor, int, str, int, int, int][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.VCTK_092.html b/main/generated/torchaudio.datasets.VCTK_092.html
index 8422dc38b97..3b1d04a653d 100644
--- a/main/generated/torchaudio.datasets.VCTK_092.html
+++ b/main/generated/torchaudio.datasets.VCTK_092.html
@@ -10,7 +10,7 @@
- VCTK_092 — Torchaudio 2.2.0.dev20240424 documentation
+ VCTK_092 — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -470,7 +470,7 @@ __getitem__
-
-VCTK_092.__getitem__(n: int) → Tuple[Tensor, int, str, str, str][source]Ā¶
+VCTK_092.__getitem__(n: int) → Tuple[Tensor, int, str, str, str][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.VoxCeleb1Identification.html b/main/generated/torchaudio.datasets.VoxCeleb1Identification.html
index 43426c64a35..c9eae0e9ed0 100644
--- a/main/generated/torchaudio.datasets.VoxCeleb1Identification.html
+++ b/main/generated/torchaudio.datasets.VoxCeleb1Identification.html
@@ -10,7 +10,7 @@
- VoxCeleb1Identification — Torchaudio 2.2.0.dev20240424 documentation
+ VoxCeleb1Identification — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -474,7 +474,7 @@ __getitem__
-
-VoxCeleb1Identification.__getitem__(n: int) → Tuple[Tensor, int, int, str][source]Ā¶
+VoxCeleb1Identification.__getitem__(n: int) → Tuple[Tensor, int, int, str][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.VoxCeleb1Verification.html b/main/generated/torchaudio.datasets.VoxCeleb1Verification.html
index f506129c2b9..a76e4247f38 100644
--- a/main/generated/torchaudio.datasets.VoxCeleb1Verification.html
+++ b/main/generated/torchaudio.datasets.VoxCeleb1Verification.html
@@ -10,7 +10,7 @@
- VoxCeleb1Verification — Torchaudio 2.2.0.dev20240424 documentation
+ VoxCeleb1Verification — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -475,7 +475,7 @@ __getitem__
-
-VoxCeleb1Verification.__getitem__(n: int) → Tuple[Tensor, Tensor, int, int, str, str][source]Ā¶
+VoxCeleb1Verification.__getitem__(n: int) → Tuple[Tensor, Tensor, int, int, str, str][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.datasets.YESNO.html b/main/generated/torchaudio.datasets.YESNO.html
index 5e3a68b9637..6b2afa485ba 100644
--- a/main/generated/torchaudio.datasets.YESNO.html
+++ b/main/generated/torchaudio.datasets.YESNO.html
@@ -10,7 +10,7 @@
- YESNO — Torchaudio 2.2.0.dev20240424 documentation
+ YESNO — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -466,7 +466,7 @@ __getitem__
-
-YESNO.__getitem__(n: int) → Tuple[Tensor, int, List[int]][source]Ā¶
+YESNO.__getitem__(n: int) → Tuple[Tensor, int, List[int]][source]Ā¶
Load the n-th sample from the dataset.
- Parameters:
diff --git a/main/generated/torchaudio.functional.DB_to_amplitude.html b/main/generated/torchaudio.functional.DB_to_amplitude.html
index 45f86332f27..a1fdb781147 100644
--- a/main/generated/torchaudio.functional.DB_to_amplitude.html
+++ b/main/generated/torchaudio.functional.DB_to_amplitude.html
@@ -10,7 +10,7 @@
- torchaudio.functional.DB_to_amplitude — Torchaudio 2.2.0.dev20240424 documentation
+ torchaudio.functional.DB_to_amplitude — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -440,7 +440,7 @@
torchaudio.functional.DB_to_amplitudeĀ¶
-
-torchaudio.functional.DB_to_amplitude(x: Tensor, ref: float, power: float) → Tensor[source]Ā¶
+torchaudio.functional.DB_to_amplitude(x: Tensor, ref: float, power: float) → Tensor[source]Ā¶
Turn a tensor from the decibel scale to the power/amplitude scale.
diff --git a/main/generated/torchaudio.functional.TokenSpan.html b/main/generated/torchaudio.functional.TokenSpan.html
index ecd9e10e9ac..8c20acabf04 100644
--- a/main/generated/torchaudio.functional.TokenSpan.html
+++ b/main/generated/torchaudio.functional.TokenSpan.html
@@ -10,7 +10,7 @@
- TokenSpan — Torchaudio 2.2.0.dev20240424 documentation
+ TokenSpan — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
diff --git a/main/generated/torchaudio.functional.add_noise.html b/main/generated/torchaudio.functional.add_noise.html
index c6d3c2a8ff5..486d6d3628d 100644
--- a/main/generated/torchaudio.functional.add_noise.html
+++ b/main/generated/torchaudio.functional.add_noise.html
@@ -10,7 +10,7 @@
- torchaudio.functional.add_noise — Torchaudio 2.2.0.dev20240424 documentation
+ torchaudio.functional.add_noise — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -440,7 +440,7 @@
torchaudio.functional.add_noiseĀ¶
-
-torchaudio.functional.add_noise(waveform: Tensor, noise: Tensor, snr: Tensor, lengths: Optional[Tensor] = None) → Tensor[source]Ā¶
+torchaudio.functional.add_noise(waveform: Tensor, noise: Tensor, snr: Tensor, lengths: Optional[Tensor] = None) → Tensor[source]Ā¶
Scales and adds noise to waveform per signal-to-noise ratio.
Specifically, for each pair of waveform vector \(x \in \mathbb{R}^L\) and noise vector
\(n \in \mathbb{R}^L\), the function computes output \(y\) as
@@ -461,10 +461,10 @@ torchaudio.functional.add_noise
- Parameters:
-waveform (torch.Tensor) ā Input waveform, with shape (ā¦, L).
-noise (torch.Tensor) ā Noise, with shape (ā¦, L) (same shape as waveform
).
-snr (torch.Tensor) ā Signal-to-noise ratios in dB, with shape (ā¦,).
-lengths (torch.Tensor or None, optional) ā Valid lengths of signals in waveform
and noise
, with shape
+
waveform (torch.Tensor) ā Input waveform, with shape (ā¦, L).
+noise (torch.Tensor) ā Noise, with shape (ā¦, L) (same shape as waveform
).
+snr (torch.Tensor) ā Signal-to-noise ratios in dB, with shape (ā¦,).
+lengths (torch.Tensor or None, optional) ā Valid lengths of signals in waveform
and noise
, with shape
(ā¦,) (leading dimensions must match those of waveform
). If None
, all elements in waveform
and noise
are treated as valid. (Default: None
)
@@ -474,7 +474,7 @@ torchaudio.functional.add_noisewaveform).
- Return type:
--
+
-
diff --git a/main/generated/torchaudio.functional.allpass_biquad.html b/main/generated/torchaudio.functional.allpass_biquad.html
index e66a3de2034..9d9c7fc003b 100644
--- a/main/generated/torchaudio.functional.allpass_biquad.html
+++ b/main/generated/torchaudio.functional.allpass_biquad.html
@@ -10,7 +10,7 @@
- torchaudio.functional.allpass_biquad — Torchaudio 2.2.0.dev20240424 documentation
+ torchaudio.functional.allpass_biquad — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -440,17 +440,17 @@
torchaudio.functional.allpass_biquadĀ¶
-
-torchaudio.functional.allpass_biquad(waveform: Tensor, sample_rate: int, central_freq: float, Q: float = 0.707) → Tensor[source]Ā¶
+torchaudio.functional.allpass_biquad(waveform: Tensor, sample_rate: int, central_freq: float, Q: float = 0.707) → Tensor[source]Ā¶
Design two-pole all-pass filter. Similar to SoX implementation.
- Parameters:
-waveform (torch.Tensor) ā audio waveform of dimension of (ā¦, time)
+waveform (torch.Tensor) ā audio waveform of dimension of (ā¦, time)
sample_rate (int) ā sampling rate of the waveform, e.g. 44100 (Hz)
-central_freq (float or torch.Tensor) ā central frequency (in Hz)
-Q (float or torch.Tensor, optional) ā https://en.wikipedia.org/wiki/Q_factor (Default: 0.707
)
+central_freq (float or torch.Tensor) ā central frequency (in Hz)
+Q (float or torch.Tensor, optional) ā https://en.wikipedia.org/wiki/Q_factor (Default: 0.707
)
- Returns:
diff --git a/main/generated/torchaudio.functional.amplitude_to_DB.html b/main/generated/torchaudio.functional.amplitude_to_DB.html
index 75967cad77f..97f308ee603 100644
--- a/main/generated/torchaudio.functional.amplitude_to_DB.html
+++ b/main/generated/torchaudio.functional.amplitude_to_DB.html
@@ -10,7 +10,7 @@
- torchaudio.functional.amplitude_to_DB — Torchaudio 2.2.0.dev20240424 documentation
+ torchaudio.functional.amplitude_to_DB — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -440,7 +440,7 @@
torchaudio.functional.amplitude_to_DBĀ¶
-
-torchaudio.functional.amplitude_to_DB(x: Tensor, multiplier: float, amin: float, db_multiplier: float, top_db: Optional[float] = None) → Tensor[source]Ā¶
+torchaudio.functional.amplitude_to_DB(x: Tensor, multiplier: float, amin: float, db_multiplier: float, top_db: Optional[float] = None) → Tensor[source]Ā¶
Turn a spectrogram from the power/amplitude scale to the decibel scale.
diff --git a/main/generated/torchaudio.functional.apply_beamforming.html b/main/generated/torchaudio.functional.apply_beamforming.html
index d01d264419a..5c52a92f640 100644
--- a/main/generated/torchaudio.functional.apply_beamforming.html
+++ b/main/generated/torchaudio.functional.apply_beamforming.html
@@ -10,7 +10,7 @@
- torchaudio.functional.apply_beamforming — Torchaudio 2.2.0.dev20240424 documentation
+ torchaudio.functional.apply_beamforming — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -440,7 +440,7 @@
torchaudio.functional.apply_beamformingĀ¶
-
-torchaudio.functional.apply_beamforming(beamform_weights: Tensor, specgram: Tensor) → Tensor[source]Ā¶
+torchaudio.functional.apply_beamforming(beamform_weights: Tensor, specgram: Tensor) → Tensor[source]Ā¶
Apply the beamforming weight to the multi-channel noisy spectrum to obtain the single-channel enhanced spectrum.
diff --git a/main/generated/torchaudio.functional.apply_codec.html b/main/generated/torchaudio.functional.apply_codec.html
index ee93383d997..0141a8d587f 100644
--- a/main/generated/torchaudio.functional.apply_codec.html
+++ b/main/generated/torchaudio.functional.apply_codec.html
@@ -10,7 +10,7 @@
- torchaudio.functional.apply_codec — Torchaudio 2.2.0.dev20240424 documentation
+ torchaudio.functional.apply_codec — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -440,7 +440,7 @@
torchaudio.functional.apply_codecĀ¶
-
-torchaudio.functional.apply_codec(waveform: Tensor, sample_rate: int, format: str, channels_first: bool = True, compression: Optional[float] = None, encoding: Optional[str] = None, bits_per_sample: Optional[int] = None) → Tensor[source]Ā¶
+torchaudio.functional.apply_codec(waveform: Tensor, sample_rate: int, format: str, channels_first: bool = True, compression: Optional[float] = None, encoding: Optional[str] = None, bits_per_sample: Optional[int] = None) → Tensor[source]Ā¶
DEPRECATED:
Apply codecs as a form of augmentation.
diff --git a/main/generated/torchaudio.functional.band_biquad.html b/main/generated/torchaudio.functional.band_biquad.html
index 29489b6fd1e..0dcf93016b8 100644
--- a/main/generated/torchaudio.functional.band_biquad.html
+++ b/main/generated/torchaudio.functional.band_biquad.html
@@ -10,7 +10,7 @@
- torchaudio.functional.band_biquad — Torchaudio 2.2.0.dev20240424 documentation
+ torchaudio.functional.band_biquad — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -440,7 +440,7 @@
torchaudio.functional.band_biquadĀ¶
-
-torchaudio.functional.band_biquad(waveform: Tensor, sample_rate: int, central_freq: float, Q: float = 0.707, noise: bool = False) → Tensor[source]Ā¶
+torchaudio.functional.band_biquad(waveform: Tensor, sample_rate: int, central_freq: float, Q: float = 0.707, noise: bool = False) → Tensor[source]Ā¶
Design two-pole band filter. Similar to SoX implementation.
@@ -449,8 +449,8 @@ torchaudio.functional.band_biquad
waveform (Tensor) ā audio waveform of dimension of (ā¦, time)
sample_rate (int) ā sampling rate of the waveform, e.g. 44100 (Hz)
-central_freq (float or torch.Tensor) ā central frequency (in Hz)
-Q (float or torch.Tensor, optional) ā https://en.wikipedia.org/wiki/Q_factor (Default: 0.707
).
+central_freq (float or torch.Tensor) ā central frequency (in Hz)
+Q (float or torch.Tensor, optional) ā https://en.wikipedia.org/wiki/Q_factor (Default: 0.707
).
noise (bool, optional) ā If True
, uses the alternate mode for un-pitched audio (e.g. percussion).
If False
, uses mode oriented to pitched audio, i.e. voice, singing,
or instrumental music (Default: False
).
diff --git a/main/generated/torchaudio.functional.bandpass_biquad.html b/main/generated/torchaudio.functional.bandpass_biquad.html
index f990e80908a..74019960d11 100644
--- a/main/generated/torchaudio.functional.bandpass_biquad.html
+++ b/main/generated/torchaudio.functional.bandpass_biquad.html
@@ -10,7 +10,7 @@
- torchaudio.functional.bandpass_biquad — Torchaudio 2.2.0.dev20240424 documentation
+ torchaudio.functional.bandpass_biquad — Torchaudio 2.2.0.dev20240503 documentation
@@ -224,7 +224,7 @@
@@ -440,7 +440,7 @@
torchaudio.functional.bandpass_biquadĀ¶
-
-torchaudio.functional.bandpass_biquad(waveform: Tensor, sample_rate: int, central_freq: float, Q: float = 0.707, const_skirt_gain: bool = False) → Tensor[source]Ā¶
+torchaudio.functional.bandpass_biquad(waveform: Tensor, sample_rate: int, central_freq: float, Q: float = 0.707, const_skirt_gain: bool = False) → Tensor[source]Ā¶
Design two-pole band-pass filter. Similar to SoX implementation.
@@ -449,8 +449,8 @@ torchaudio.functional.bandpass_biquad