extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-01-13 09:28:35 +01:00
Code Issues Packages Projects Releases Wiki Activity

common : fix wav buffer detection (#1819)

Browse Source
This commit is contained in:
JacobLinCool 2024-01-31 01:35:08 +08:00 committed by GitHub
parent baa30bacdb
commit ae5c4f7340
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 19 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
examples/common.cpp
View File

@ -615,6 +615,21 @@ gpt_vocab::id gpt_sample_top_k_top_p_repeat(
}
bool is_wav_buffer(const std::string buf) {
// RIFF ref: https://en.wikipedia.org/wiki/Resource_Interchange_File_Format
// WAV ref: https://www.mmsp.ece.mcgill.ca/Documents/AudioFormats/WAVE/WAVE.html
if (buf.size() < 12 || buf.substr(0, 4) != "RIFF" || buf.substr(8, 4) != "WAVE") {
return false;
}
uint32_t chunk_size = *reinterpret_cast<const uint32_t*>(buf.data() + 4);
if (chunk_size + 8 != buf.size()) {
return false;
}
return true;
}
bool read_wav(const std::string & fname, std::vector<float>& pcmf32, std::vector<std::vector<float>>& pcmf32s, bool stereo) {
drwav wav;
std::vector<uint8_t> wav_data; // used for pipe input from stdin
@ -639,7 +654,7 @@ bool read_wav(const std::string & fname, std::vector<float>& pcmf32, std::vector
fprintf(stderr, "%s: read %zu bytes from stdin\n", __func__, wav_data.size());
}
else if (fname.size() > 256 && (fname.substr(0, 4) == "RIFF" || fname.substr(8, 4) == "WAVE")) {
else if (is_wav_buffer(fname)) {
if (drwav_init_memory(&wav, fname.c_str(), fname.size(), nullptr) == false) {
fprintf(stderr, "error: failed to open WAV file from fname buffer\n");
return false;

3
examples/common.h
View File

@ -135,6 +135,9 @@ gpt_vocab::id gpt_sample_top_k_top_p_repeat(
// Audio utils
//
// Check if a buffer is a WAV audio file
bool is_wav_buffer(const std::string buf);
// Read WAV audio file and store the PCM data into pcmf32
// fname can be a buffer of WAV data instead of a filename
// The sample rate of the audio must be equal to COMMON_SAMPLE_RATE