Could the author of PromptTTS2 provide a script that uses an SLU model to obtain classification results for different attributes of speech?
The article only references two papers regarding SLU models: "wav2vec 2.0: A framework for self-supervised learning of speech representations" and "Espnet-slu: Advancing spoken language understanding through espnet." However, I couldn't seem to find the code or implementation of these two papers for Speech Attribute Classification.
Could the author of PromptTTS2 provide a script that uses an SLU model to obtain classification results for different attributes of speech? The article only references two papers regarding SLU models: "wav2vec 2.0: A framework for self-supervised learning of speech representations" and "Espnet-slu: Advancing spoken language understanding through espnet." However, I couldn't seem to find the code or implementation of these two papers for Speech Attribute Classification.