Not working for multiple sentences

Describe the bug

When I send more than one sentence, it is giving me the error.

To Reproduce

Input Text: a tree is a perennial plant with an elongated stem, or trunk, usually supporting branches and leaves. In some usages, the definition of a tree may be narrower, including only woody plants with secondary growth, plants that are usable as lumber or plants above a specified height.

import os from TTS.api import TTS TTS_MODEL_PATH = "tts_models/multilingual/multi-dataset/xtts_v2" tts = TTS(model_name=TTS_MODEL_PATH, gpu=True)

def text_to_speech(text, speaker_wav_file, language, output_path): os.makedirs(os.path.dirname(output_path), exist_ok=True) tts.tts_to_file(text, speaker_wav=speaker_wav_file, language=language, file_path=output_path) return output_path

@app.route('/text-to-speech', methods=['POST']) def text_to_speech_api(): try: text = request.form.get('text') language = request.form.get('language') speaker_wav_file = request.files['speaker_wav'] output_path = '/data/ai-tools/voice_cloning/output.wav' # Update this with the actual path output_file = text_to_speech(text, speaker_wav_file, language, output_path) return send_file(output_file) except Exception as e: return str(e), 500

Expected behavior

No response

Logs

Getting Error: Failed to open the input "Custom Input Context" (Invalid data found when
processing input).
Exception raised from get_input_format_context at
/__w/audio/audio/pytorch/audio/torchaudio/csrc/ffmpeg/stream_reader/stream_reader.cpp:42
(most recent call first):
frame #0: c10::Error::Error(c10::SourceLocation, std::string) + 0x57
(0x7f4ea370f617 in
/data/ai-tools/venv/lib64/python3.9/site-packages/torch/lib/libc10.so)
frame #1: c10::detail::torchCheckFail(char const*, char const*, unsigned int,
std::string const&) + 0x64 (0x7f4ea36ca98d in
/data/ai-tools/venv/lib64/python3.9/site-packages/torch/lib/libc10.so)
frame #2: <unknown function> + 0x43944 (0x7f4d9c583944 in
  /data/ai-tools/venv/lib/python3.9/site-packages/torchaudio/lib/libtorchaudio_ffmpeg6.so)
  frame #3: torchaudio::io::StreamReader::StreamReader(AVIOContext*,
  c10::optional<std::string> const&, c10::optional<std::map<std::string,
      std::string, std::less<std::string>, std::allocator<std::pair<std::string
        const, std::string> > > > const&) + 0x43 (0x7f4d9c586283 in
        /data/ai-tools/venv/lib/python3.9/site-packages/torchaudio/lib/libtorchaudio_ffmpeg6.so)
        frame #4:
        torchaudio::io::StreamReaderCustomIO::StreamReaderCustomIO(void*,
        c10::optional<std::string> const&, int, int (*)(void*, unsigned char*,
          int), long (*)(void*, long, int), c10::optional<std::map<std::string,
            std::string, std::less<std::string>,
            std::allocator<std::pair<std::string const, std::string> > > >
              const&) + 0x2f (0x7f4d9c58631f in
              /data/ai-tools/venv/lib/python3.9/site-packages/torchaudio/lib/libtorchaudio_ffmpeg6.so)
              frame #5: <unknown function> + 0x17a89 (0x7f4d9c47aa89 in
                /data/ai-tools/venv/lib64/python3.9/site-packages/torchaudio/lib/_torchaudio_ffmpeg6.so)
                frame #6: <unknown function> + 0x2de35 (0x7f4d9c490e35 in
                  /data/ai-tools/venv/lib64/python3.9/site-packages/torchaudio/lib/_torchaudio_ffmpeg6.so)
                  <omitting python frames>
                    frame #12: <unknown function> + 0xf744 (0x7f4dc5a20744 in
                      /data/ai-tools/venv/lib64/python3.9/site-packages/torchaudio/lib/_torchaudio.so)

Environment

TTS Version: 2
AWS EC2
ffmpeg version N-112128-gfa20f5cd9e Copyright (c) 2000-2023 the FFmpeg developers
  built with gcc 11 (GCC)
  configuration: --enable-shared --disable-static --enable-gpl --enable-libfreetype
  libavutil      58. 25.100 / 58. 25.100
  libavcodec     60. 26.100 / 60. 26.100
  libavformat    60. 13.100 / 60. 13.100
  libavdevice    60.  2.101 / 60.  2.101
  libavfilter     9. 11.100 /  9. 11.100
  libswscale      7.  3.100 /  7.  3.100
  libswresample   4. 11.100 /  4. 11.100
  libpostproc    57.  2.100 / 57.  2.100

Additional context

No response

coqui-ai / TTS