| processor_output = processor(raw_speech=sample["array"], sampling_rate=sample["sampling_rate"], text=text, return_tensors="pt") | |
| generated_output = model.generate(**processor_output) | |
| ClvpConfig | |
| [[autodoc]] ClvpConfig | |
| - from_sub_model_configs | |
| ClvpEncoderConfig | |
| [[autodoc]] ClvpEncoderConfig | |
| ClvpDecoderConfig | |
| [[autodoc]] ClvpDecoderConfig | |
| ClvpTokenizer | |
| [[autodoc]] ClvpTokenizer | |
| - save_vocabulary | |
| ClvpFeatureExtractor | |
| [[autodoc]] ClvpFeatureExtractor | |
| - call | |
| ClvpProcessor | |
| [[autodoc]] ClvpProcessor | |
| - call | |
| - decode | |
| - batch_decode | |
| ClvpModelForConditionalGeneration | |
| [[autodoc]] ClvpModelForConditionalGeneration | |
| - forward | |
| - generate | |
| - get_text_features | |
| - get_speech_features | |
| ClvpForCausalLM | |
| [[autodoc]] ClvpForCausalLM | |
| ClvpModel | |
| [[autodoc]] ClvpModel | |
| ClvpEncoder | |
| [[autodoc]] ClvpEncoder | |
| ClvpDecoder | |
| [[autodoc]] ClvpDecoder |