// convert to mono, float
pcmf32.resize(n);
if (wav.channels == 1) {
- for (int i = 0; i < n; i++) {
+ for (uint64_t i = 0; i < n; i++) {
pcmf32[i] = float(pcm16[i])/32768.0f;
}
} else {
- for (int i = 0; i < n; i++) {
+ for (uint64_t i = 0; i < n; i++) {
pcmf32[i] = float(pcm16[2*i] + pcm16[2*i + 1])/65536.0f;
}
}
pcmf32s[0].resize(n);
pcmf32s[1].resize(n);
- for (int i = 0; i < n; i++) {
+ for (uint64_t i = 0; i < n; i++) {
pcmf32s[0][i] = float(pcm16[2*i])/32768.0f;
pcmf32s[1][i] = float(pcm16[2*i + 1])/32768.0f;
}
int whisper_tokenize(struct whisper_context * ctx, const char * text, whisper_token * tokens, int n_max_tokens) {
const auto res = tokenize(ctx->vocab, text);
- if (res.size() > n_max_tokens) {
+ if (n_max_tokens < (int) res.size()) {
fprintf(stderr, "%s: too many resulting tokens: %d (max %d)\n", __func__, (int) res.size(), n_max_tokens);
return -1;
}
- for (int i = 0; i < res.size(); i++) {
+ for (int i = 0; i < (int) res.size(); i++) {
tokens[i] = res[i];
}
}
std::vector<std::pair<float, int>> probs_id;
- for (const auto kv : g_lang) {
+ for (const auto & kv : g_lang) {
const auto token_lang = whisper_token_lang(ctx, kv.second.first);
probs_id.push_back({ ctx->probs[token_lang], kv.second.first });
}
}
{
- for (int i = 0; i < probs_id.size(); i++) {
+ for (int i = 0; i < (int) probs_id.size(); i++) {
if (lang_probs) {
lang_probs[probs_id[i].second] = probs_id[i].first;
}
struct whisper_context * ctx,
const char * text,
whisper_token * tokens,
- int n_max_tokens);
+ int n_max_tokens);
// Largest language id (i.e. number of available languages - 1)
WHISPER_API int whisper_lang_max_id();