Support Zipformer transducer ASR with whisper features. (#2321)
Adds support for Zipformer transducer ASR models that use Whisper-style features by introducing a new feature flag, parsing metadata, and integrating per-chunk normalization. - Introduce UseWhisperFeature in the model interface and Zipformer implementation - Parse "feature" metadata to set the whisper flag and wire it into the recognizer - Update feature extraction logic to handle Whisper filterbanks with early returns
This commit is contained in:
@@ -131,10 +131,13 @@ class FeatureExtractor::Impl {
|
||||
std::lock_guard<std::mutex> lock(mutex_);
|
||||
if (fbank_) {
|
||||
fbank_->InputFinished();
|
||||
return;
|
||||
} else if (whisper_fbank_) {
|
||||
whisper_fbank_->InputFinished();
|
||||
return;
|
||||
} else if (mfcc_) {
|
||||
mfcc_->InputFinished();
|
||||
return;
|
||||
}
|
||||
|
||||
SHERPA_ONNX_LOGE("unreachable code");
|
||||
|
||||
Reference in New Issue
Block a user