Output json from server

[markohlavaty]

Change default output format to json for the server. The json contains timestamps for start and end of segment, its text, its token IDs, and for each word of the segment, it also contains its start and end, its text, and its token IDs. The timestamps in the json format are in seconds, not in milliseconds.

The original output format can still be enabled by passing the argument --out-txt.

📄 Contributor License Agreement Consent

The authors of SimulStreaming wish to enhance ways to collect and use feedback from users of SimulStreaming in future research and development while not limiting community contributions and non-commercial use. Therefore, this project is dual-licenced; the commercial use requires registration before obtaining a commercial licence.

Before we merge this pull request, we kindly ask you to consider granting the permissions below. If you have questions or prefer a different arrangement, feel free to leave a comment or contact the author. Thank you!

By checking the boxes below, you confirm the following:

• I confirm that I have the legal right to grant a license for the contributions in this pull request to the maintainers of the SimulStreaming project.
  (For example, you are the only author, of legal age, not restricted by employment or institutional agreements.)

• [X ] I grant the maintainers of SimulStreaming permission to re-license my contribution under any license, including commercial ones.

[russellpierce]

Does this change the default response from text to json?