limitations

One limitation of the project is the limited availability of data for training the Dzongkha Text-to-Speech (TTS) system, which may impact the robustness and generalization of the model. The choice of the Graffin Lim vocoder, although suitable given the available resources, may not achieve the same level of quality as more advanced vocoders that were not explored due to constraints. Another limitation is the duration restriction on the output speech, necessitating the segmentation and concatenation of speech segments. This process can introduce prosodic errors and disrupt the natural flow of synthesized speech. These limitations should be taken into account when evaluating the quality and fluency of the synthesized output.