torchaudio 0.4.0 → 0.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 938d840ca33f543f9ae76e911fe9681448703dddaab35a1a9dc05703a19d42c0
-  data.tar.gz: 5bac1684448eac1c520d2f4e5f17ac0ac7948afc7a2e46bb4bc5cd721a66ef26
+  metadata.gz: 1d221dc6cf08b75a5084dcd0142067168c3a03302e5dbd638f0f68ed7882ad31
+  data.tar.gz: acc470a5f1ab004ec0a42e9229bbfc5321434328496f165f932a217a3d106220
 SHA512:
-  metadata.gz: 01f602344f23934a80470c72a2608f64209fd3649c614d107f6a87757774a6930a14e83fc421cb4f35a629d41f4321b1967849c0f05aa3c6a580b69814bfe637
-  data.tar.gz: 908bb885c92f1748c6f38609ea02b44fdf187bace3fafffd4764348516d5cf590fdb9aafb3871de5a9feacdcb9bd96cefead9753092b8c5d8711a1a63ae57aef
+  metadata.gz: e49dec118b6886295f44aa01452ffc6f3f0dedae8debbb6c094a33dcb8ca388c3336581af53ceb0fbe25e0689ac7ceba1bee0c3b1b172019405fc7a4240a32b0
+  data.tar.gz: 0b1fc5854e251137cba56279219d9c307b98811083f127be282f8229c46d80e667145773967d75afedf0b33a4ecf6af39f437c83b9844a11fab435d25b265df3

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.4.1 (2025-06-26)
+
+- Improved SoX detection for Homebrew
+
 ## 0.4.0 (2024-08-02)
 
 - Dropped support for Ruby < 3.1

data/LICENSE.txt

@@ -1,7 +1,7 @@
 BSD 2-Clause License
 
 Copyright (c) 2017 Facebook Inc. (Soumith Chintala),
-Copyright (c) 2020-2024 Andrew Kane,
+Copyright (c) 2020-2025 Andrew Kane,
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

data/README.md

@@ -93,7 +93,7 @@ TorchAudio::Datasets::YESNO.new(".", download: true)
 
 Supported datasets are:
 
-- [YESNO](http://www.openslr.org/1/)
+- [YESNO](https://www.openslr.org/1/)
 
 ## Disclaimer
 

data/ext/torchaudio/csrc/sox_utils.cpp

@@ -44,7 +44,7 @@ void validate_input_file(const SoxFormat& sf) {
     throw std::runtime_error("Error loading audio file: unknown encoding.");
   }
   if (sf->signal.length == 0) {
-    throw std::runtime_error("Error reading audio file: unkown length.");
+    throw std::runtime_error("Error reading audio file: unknown length.");
   }
 }
 
@@ -84,7 +84,7 @@ caffe2::TypeMeta get_dtype(
         }
       default:
         // default to float32 for the other formats, including
-        // 32-bit flaoting-point WAV,
+        // 32-bit floating-point WAV,
         // MP3,
         // FLAC,
         // VORBIS etc...

data/ext/torchaudio/ext.cpp

@@ -1,11 +1,12 @@
+#include <string>
+
 #include <torchaudio/csrc/sox.h>
 
 #include <rice/rice.hpp>
 #include <rice/stl.hpp>
 
 extern "C"
-void Init_ext()
-{
+void Init_ext() {
   auto rb_mTorchAudio = Rice::define_module("TorchAudio");
 
   auto rb_mExt = Rice::define_module_under(rb_mTorchAudio, "Ext")

data/ext/torchaudio/extconf.rb

@@ -73,6 +73,12 @@ if with_cuda
   $LDFLAGS += " -Wl,--no-as-needed,#{lib}/libtorch.so"
 end
 
+sox_inc, sox_lib = dir_config("sox")
+sox_inc ||= paths.map { |v| "#{v}/include" }.find { |v| File.exist?("#{v}/sox.h") }
+sox_lib ||= paths.map { |v| "#{v}/lib" }.find { |v| Dir["#{v}/*libsox*"].any? }
+
+$INCFLAGS += " -I#{sox_inc}" if sox_inc
+$LDFLAGS += " -L#{sox_lib}" if sox_lib
 abort "SoX not found" unless have_library("sox")
 
 # create makefile

data/lib/torchaudio/transforms/mel_spectrogram.rb

@@ -4,11 +4,19 @@ module TorchAudio
       attr_reader :n_mels
 
       def initialize(
-        sample_rate: 16000, n_fft: 400, win_length: nil, hop_length: nil, f_min: 0.0,
-        f_max: nil, pad: 0, n_mels: 128, window_fn: Torch.method(:hann_window),
-        power: 2.0, normalized: false, wkwargs: nil
+        sample_rate: 16000,
+        n_fft: 400,
+        win_length: nil,
+        hop_length: nil,
+        f_min: 0.0,
+        f_max: nil,
+        pad: 0,
+        n_mels: 128,
+        window_fn: Torch.method(:hann_window),
+        power: 2.0,
+        normalized: false,
+        wkwargs: nil
       )
-
         super()
         @sample_rate = sample_rate
         @n_fft = n_fft

data/lib/torchaudio/transforms/spectrogram.rb

@@ -2,11 +2,18 @@ module TorchAudio
   module Transforms
     class Spectrogram < Torch::NN::Module
       def initialize(
-        n_fft: 400, win_length: nil, hop_length: nil, pad: 0,
-        window_fn: Torch.method(:hann_window), power: 2.0, normalized: false, wkwargs: nil,
-        center: true, pad_mode: "reflect", onesided: true
+        n_fft: 400,
+        win_length: nil,
+        hop_length: nil,
+        pad: 0,
+        window_fn: Torch.method(:hann_window),
+        power: 2.0,
+        normalized: false,
+        wkwargs: nil,
+        center: true,
+        pad_mode: "reflect",
+        onesided: true
       )
-
         super()
         @n_fft = n_fft
         # number of FFT bins. the returned STFT result will have n_fft // 2 + 1

data/lib/torchaudio/version.rb

@@ -1,3 +1,3 @@
 module TorchAudio
-  VERSION = "0.4.0"
+  VERSION = "0.4.1"
 end

data/lib/torchaudio.rb

@@ -32,10 +32,17 @@ module TorchAudio
   class << self
     # TODO remove filetype in 0.4.0
     def load(
-      filepath, out: nil, normalization: true, channels_first: true, num_frames: 0,
-      offset: 0, signalinfo: nil, encodinginfo: nil, filetype: nil, format: nil
+      filepath,
+      out: nil,
+      normalization: true,
+      channels_first: true,
+      num_frames: 0,
+      offset: 0,
+      signalinfo: nil,
+      encodinginfo: nil,
+      filetype: nil,
+      format: nil
     )
-
       filepath = filepath.to_s
 
       # check if valid file

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: torchaudio
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.4.1
 platform: ruby
 authors:
 - Andrew Kane
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-08-03 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: torch-rb
@@ -30,15 +29,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '4.3'
+        version: 4.3.3
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '4.3'
-description:
+        version: 4.3.3
 email: andrew@ankane.org
 executables: []
 extensions:
@@ -78,7 +76,6 @@ homepage: https://github.com/ankane/torchaudio-ruby
 licenses:
 - BSD-2-Clause
 metadata: {}
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -93,8 +90,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.11
-signing_key:
+rubygems_version: 3.6.7
 specification_version: 4
 summary: Data manipulation and transformation for audio signal processing
 test_files: []