[Bug] Very long audio synthesized from "hi" using Tacotron2-DDC

[shaiperson]

Describe the bug

I tried to synthesize the text "hi" using tts_models/en/ljspeech/tacotron2-DDC. The output is consistently a ~1:50 long audio the extends the word "hi" (quite disconcertingly) for the whole duration. I tried both using the library directly and through the demo server. This didn't happen with other models I tried (namely tts_models/en/ljspeech/tacotron2-DDC_ph and tts_models/en/ljspeech/glow-tts).

To Reproduce

Run the following code:

import torch
from TTS.api import TTS

device = "cuda" if torch.cuda.is_available() else "cpu"

tts = TTS("tts_models/en/ljspeech/tacotron2-DDC").to(device)

tts.tts_to_file(text="hi", file_path='output.wav')

Expected behavior

A short audio of the word "hi".

Logs

> tts_models/en/ljspeech/tacotron2-DDC is already downloaded.
 > vocoder_models/en/ljspeech/hifigan_v2 is already downloaded.
 > Using model: Tacotron2
 > Setting up Audio Processor...
 | > sample_rate:22050
 | > resample:False
 | > num_mels:80
 | > log_func:np.log
 | > min_level_db:-100
 | > frame_shift_ms:None
 | > frame_length_ms:None
 | > ref_level_db:20
 | > fft_size:1024
 | > power:1.5
 | > preemphasis:0.0
 | > griffin_lim_iters:60
 | > signal_norm:False
 | > symmetric_norm:True
 | > mel_fmin:0
 | > mel_fmax:8000.0
 | > pitch_fmin:1.0
 | > pitch_fmax:640.0
 | > spec_gain:1.0
 | > stft_pad_mode:reflect
 | > max_norm:4.0
 | > clip_norm:True
 | > do_trim_silence:True
 | > trim_db:60
 | > do_sound_norm:False
 | > do_amp_to_db_linear:True
 | > do_amp_to_db_mel:True
 | > do_rms_norm:False
 | > db_level:None
 | > stats_path:None
 | > base:2.718281828459045
 | > hop_length:256
 | > win_length:1024
/Users/shai/speech-bot/repo/TTS/TTS/utils/io.py:54: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  return torch.load(f, map_location=map_location, **kwargs)

 > Model's reduction rate `r` is set to: 1
 > Vocoder Model: hifigan
 > Setting up Audio Processor...
 | > sample_rate:22050
 | > resample:False
 | > num_mels:80
 | > log_func:np.log
 | > min_level_db:-100
 | > frame_shift_ms:None
 | > frame_length_ms:None
 | > ref_level_db:20
 | > fft_size:1024
 | > power:1.5
 | > preemphasis:0.0
 | > griffin_lim_iters:60
 | > signal_norm:False
 | > symmetric_norm:True
 | > mel_fmin:0
 | > mel_fmax:8000.0
 | > pitch_fmin:1.0
 | > pitch_fmax:640.0
 | > spec_gain:1.0
 | > stft_pad_mode:reflect
 | > max_norm:4.0
 | > clip_norm:True
 | > do_trim_silence:False
 | > trim_db:60
 | > do_sound_norm:False
 | > do_amp_to_db_linear:True
 | > do_amp_to_db_mel:True
 | > do_rms_norm:False
 | > db_level:None
 | > stats_path:None
 | > base:2.718281828459045
 | > hop_length:256
 | > win_length:1024
 > Generator Model: hifigan_generator
 > Discriminator Model: hifigan_discriminator
Removing weight norm...
 > Text splitted to sentences.
['hi']
   > Decoder stopped with `max_decoder_steps` 10000
 > Processing time: 21.41048312187195
 > Real-time factor: 0.1835141465455719

Environment

{
    "CUDA": {
        "GPU": [],
        "available": false,
        "version": null
    },
    "Packages": {
        "PyTorch_debug": false,
        "PyTorch_version": "2.5.1",
        "TTS": "0.22.0",
        "numpy": "1.26.4"
    },
    "System": {
        "OS": "Darwin",
        "architecture": [
            "64bit",
            ""
        ],
        "processor": "arm",
        "python": "3.11.9",
        "version": "Darwin Kernel Version 22.1.0: Sun Oct  9 20:19:12 PDT 2022; root:xnu-8792.41.9~3/RELEASE_ARM64_T6020"
    }
}

Additional context

No response