Hindi Doesn't Work.

[bishtyyy]

When i select hindi from language section and press on generate i get the following error message - Using ready reference Using folder reference None test C:\Tools\xtts-webui\temp\resampled_audio_8657cc3a-7662-40ec-b5f9-d0f93f283953.wav Test Traceback (most recent call last): File "C:\Tools\xtts-webui\venv\lib\site-packages\gradio\queueing.py", line 489, in call_prediction output = await route_utils.call_process_api( File "C:\Tools\xtts-webui\venv\lib\site-packages\gradio\route_utils.py", line 232, in call_process_api output = await app.get_blocks().process_api( File "C:\Tools\xtts-webui\venv\lib\site-packages\gradio\blocks.py", line 1561, in process_api result = await self.call_function( File "C:\Tools\xtts-webui\venv\lib\site-packages\gradio\blocks.py", line 1179, in call_function prediction = await anyio.to_thread.run_sync( File "C:\Tools\xtts-webui\venv\lib\site-packages\anyio\to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "C:\Tools\xtts-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 2144, in run_sync_in_worker_thread return await future File "C:\Tools\xtts-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 851, in run result = context.run(func, *args) File "C:\Tools\xtts-webui\venv\lib\site-packages\gradio\utils.py", line 678, in wrapper response = f(*args, **kwargs) File "C:\Tools\xtts-webui\modules\text2voice\generation.py", line 592, in generate_audio output_file = XTTS.process_tts_to_file( File "C:\Tools\xtts-webui\scripts\tts_funcs.py", line 443, in process_tts_to_file raise e # Propagate exceptions for endpoint handling. File "C:\Tools\xtts-webui\scripts\tts_funcs.py", line 433, in process_tts_to_file self.local_generation( File "C:\Tools\xtts-webui\scripts\tts_funcs.py", line 335, in local_generation out = self.model.inference( File "C:\Tools\xtts-webui\venv\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "C:\Tools\xtts-webui\venv\lib\site-packages\TTS\tts\models\xtts.py", line 526, in inference text = split_sentence(text, language, self.tokenizer.char_limits[language]) KeyError: 'hi'

I have reinstalled the entire program 3-4 times with all necessarcy files and dependencies and it still gives me same error. All the other languages are working fine only hindi is not working. Please look into this and fix the error.

[iamjamilkhan]

Same here I’m facing this issue but no update from developer

[bishtyyy]

Same here I’m facing this issue but no update from developer i manually installed using the methods provided in the github.. i managed to bypass this error..but the generated hindi audio is total gibberish... its just random sounds..like umm or ahh ...

[rajeshjsl]

Same here I’m facing this issue but no update from developer i manually installed using the methods provided in the github.. i managed to bypass this error..but the generated hindi audio is total gibberish... its just random sounds..like umm or ahh ...

Have the same issue.

Gibberish output on models 2.0.2 and 2.0.3.