Update README.md

README.md

@@ -99,6 +99,8 @@ with torch.no_grad():
 torchaudio.save("tts.wav", recon[0, :, :], 24_000)
 ```
 
+For even higher fidelity in German speech, use our [finetuned NeuCodec decoder](https://huggingface.co/DigitalLearningGmbH/neucodec-decoder-ft-de).
+
 ### What's to come
 
 As stated in the model's name, this is a preview model, mainly meant to showcase the capability of the base model.
@@ -107,8 +109,7 @@ We trained on a small dataset of a single speaker without any special emotion ta
 We are actively working on
  - multiple speakers with emotional control and nonverbal elements (fillers, laughing, ...)
  - fine-tuning for general zero-shot voice cloning
+ - phoneme-based / hybrid generation
  - post-training with reinforcement learning
 
-Also, we have a fine-tuned version of NeuCodec which we used to generate the speech examples above, which we also plan on realeasing.
-
 Stay tuned - january 2026 is going to be exciting!