Docs

Author: NicolasHug

examples/audio_decoding.py

@@ -20,9 +20,11 @@
 import requests
 from IPython.display import Audio
 
+
 def play_audio(samples):
     return Audio(samples.data, rate=samples.sample_rate)
 
+
 # Audio source is CC0: https://opengameart.org/content/town-theme-rpg
 # Attribution: cynicmusic.com pixelsphere.org
 url = "https://opengameart.org/sites/default/files/TownTheme.mp3"
@@ -61,6 +63,7 @@ def play_audio(samples):
 # which returns an :class:`~torchcodec.AudioSamples` object:
 
 samples = decoder.get_samples_played_in_range(start_seconds=0)
+
 print(samples)
 play_audio(samples)
 
@@ -76,16 +79,21 @@ def play_audio(samples):
 # the entire audio stream, but we can specify a custom range:
 
 samples = decoder.get_samples_played_in_range(start_seconds=10, stop_seconds=70)
+
+print(samples)
 play_audio(samples)
 
+# %%
 # Custom sample rate
 # ------------------
 #
 # We can also decode the samples into a desired sample rate using the
-# ``sample_rate`` parameter of :class:`~torchcodec.decoders.AudioDecoder`:
+# ``sample_rate`` parameter of :class:`~torchcodec.decoders.AudioDecoder`. The
+# ouput will sound the same, but note that the number of samples greatly
+# increased:
 
-sample_rate = 16_000
-decoder = AudioDecoder(raw_audio_bytes, sample_rate=sample_rate)
+decoder = AudioDecoder(raw_audio_bytes, sample_rate=16_000)
 samples = decoder.get_samples_played_in_range(start_seconds=0)
+
 print(samples)
 play_audio(samples)

src/torchcodec/decoders/__init__.py

@@ -4,8 +4,8 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+from ._audio_decoder import AudioDecoder  # noqa
 from ._core import AudioStreamMetadata, VideoStreamMetadata
 from ._video_decoder import VideoDecoder  # noqa
-from ._audio_decoder import AudioDecoder # noqa
 
 SimpleVideoDecoder = VideoDecoder

src/torchcodec/decoders/_audio_decoder.py

@@ -24,7 +24,7 @@ class AudioDecoder:
     etc.), or from videos that contain audio streams (e.g. mp4 videos).
 
     Returned samples are float samples normalized in [-1, 1]
-    
+
     Args:
         source (str, ``Pathlib.path``, ``torch.Tensor``, or bytes): The source of the audio: