in torchaudio/csrc/sox/io.cpp [73:130]
void save_audio_file(
const std::string& path,
torch::Tensor tensor,
int64_t sample_rate,
bool channels_first,
c10::optional<double> compression,
c10::optional<std::string> format,
c10::optional<std::string> encoding,
c10::optional<int64_t> bits_per_sample) {
validate_input_tensor(tensor);
const auto filetype = [&]() {
if (format.has_value())
return format.value();
return get_filetype(path);
}();
if (filetype == "amr-nb") {
const auto num_channels = tensor.size(channels_first ? 0 : 1);
TORCH_CHECK(
num_channels == 1, "amr-nb format only supports single channel audio.");
} else if (filetype == "htk") {
const auto num_channels = tensor.size(channels_first ? 0 : 1);
TORCH_CHECK(
num_channels == 1, "htk format only supports single channel audio.");
} else if (filetype == "gsm") {
const auto num_channels = tensor.size(channels_first ? 0 : 1);
TORCH_CHECK(
num_channels == 1, "gsm format only supports single channel audio.");
TORCH_CHECK(
sample_rate == 8000,
"gsm format only supports a sampling rate of 8kHz.");
}
const auto signal_info =
get_signalinfo(&tensor, sample_rate, filetype, channels_first);
const auto encoding_info = get_encodinginfo_for_save(
filetype, tensor.dtype(), compression, encoding, bits_per_sample);
SoxFormat sf(sox_open_write(
path.c_str(),
&signal_info,
&encoding_info,
/*filetype=*/filetype.c_str(),
/*oob=*/nullptr,
/*overwrite_permitted=*/nullptr));
if (static_cast<sox_format_t*>(sf) == nullptr) {
throw std::runtime_error(
"Error saving audio file: failed to open file " + path);
}
torchaudio::sox_effects_chain::SoxEffectsChain chain(
/*input_encoding=*/get_tensor_encodinginfo(tensor.dtype()),
/*output_encoding=*/sf->encoding);
chain.addInputTensor(&tensor, sample_rate, channels_first);
chain.addOutputFile(sf);
chain.run();
}