Loading Qwen3-TTS 1.7B...
/bin/sh: 1: sox: not found
SoX could not be found!

    If you do not have SoX, proceed here:
     - - - http://sox.sourceforge.net/ - - -

    If you do (or think that you should) have SoX, double-check your
    path variables.
    
`torch_dtype` is deprecated! Use `dtype` instead!

Fetching 4 files:   0%|          | 0/4 [00:00<?, ?it/s]
Fetching 4 files:  25%|██▌       | 1/4 [00:00<00:01,  2.16it/s]
Fetching 4 files:  75%|███████▌  | 3/4 [00:02<00:00,  1.43it/s]
Fetching 4 files: 100%|██████████| 4/4 [00:02<00:00,  1.98it/s]
Model loaded. GPU: NVIDIA A100-SXM4-80GB
VRAM: 4.2GB

Warming up...
Traceback (most recent call last):
  File "/home/ubuntu/qwen3_tts_test.py", line 36, in <module>
    audio_list, sr = model.generate_voice_clone(
  File "/home/ubuntu/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/home/ubuntu/.local/lib/python3.10/site-packages/faster_qwen3_tts/model.py", line 568, in generate_voice_clone
    m, talker, config, tie, tam, tth, tpe, ref_codes = self._prepare_generation(
  File "/home/ubuntu/.local/lib/python3.10/site-packages/faster_qwen3_tts/model.py", line 240, in _prepare_generation
    tie, tam, tth, tpe = self._build_talker_inputs_local(
  File "/home/ubuntu/.local/lib/python3.10/site-packages/faster_qwen3_tts/model.py", line 354, in _build_talker_inputs_local
    raise NotImplementedError(f"Language {language} not implemented")
NotImplementedError: Language Hindi not implemented