|
|
|
|
|
|
by luke-stanley
206 days ago
|
|
|
I'd lower the temperature and try DSPy Refine loop on it (or similar). Using audio encoder-decoder models and segmentation are good things to try too. A length mismatch would be bad. DSPy has optimisers. It could probably optimise well with length match heuristic, there is probably a good Shannon entropy rule. |
|
|