[OpenVINO] Support ResembleAI/chatterbox text-to-speech

[openvino-agent]

What does this PR do?

Set up environment

pip install chatterbox-tts
pip install optimum-intel@

Export model

optimum-cli export openvino -m ResembleAI/chatterbox chatterbox

Infer the model:

import os

import soundfile as sf

from optimum.exporters.openvino import main_export
from optimum.intel import OVModelForTextToSpeechSeq2Seq

OV_MODEL_DIR = "./chatterbox"


model = OVModelForTextToSpeechSeq2Seq.from_pretrained(OV_MODEL_DIR)

samples = {
    "en": "Hello, this is the multilingual text-to-speech model with OpenVINO.",
    "fr": "Bonjour, comment ça va? Ceci est le modèle de synthèse vocale multilingue.",
    "de": "Hallo, dies ist das mehrsprachige Text-zu-Sprache-Modell mit OpenVINO.",
}

for language_id, text in samples.items():
    waveform = model.generate(text=text, language_id=language_id)
    out_path = f"test-{language_id}-ov.wav"
    sf.write(out_path, waveform.squeeze().numpy(), model.sampling_rate)
    print(f"[{language_id}] saved {out_path} ({waveform.shape[-1] / model.sampling_rate:.2f}s)")

Fixes # (issue)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

[regisss]

This test will not be launched in any workflow unless the chatterbox-tts package is manually installed, is that intended?

[regisss]

Same question