license: cc0-1.0
language:
- cs
base_model:
- ResembleAI/chatterbox
pipeline_tag: text-to-speech
Chatterbox Czech
training quality TTS with low ressource data
demo audios:
"Dobrý den, vítáme vás v našem testu syntézy řeči"
"Tři sta třiatřicet stříbrných křepelek přeletělo přes tři stříbrné střechy"
"Kolik stojí devět tisíc osm set sedmdesát pět korun ?"
"Prosím, nastav hlasitost na sedmdesát procent a přehraj znovu"
"Doktor Křivohlavý napsal článek o umělé inteligenci"
"Zvon zvoní, z dálky zní, ozvěna se vrací do údolí"
💻 Inference Code
First, download the file from huggingface and place it in the current directory.
The pypi version is delayed, so you must use the github version.
!git clone https://github.com/resemble-ai/chatterbox.git chatterbox_git
pip install chatterbox-tts
from chatterbox_git.src.chatterbox import mtl_tts
import torchaudio as ta
from safetensors.torch import load_file as load_safetensors
device = "cpu" # or mps or cuda
multilingual_model = mtl_tts.ChatterboxMultilingualTTS.from_pretrained(device=device)
# ----
# Then download the file from huggingface and place it in the current directory.
# ----
t3_state = load_safetensors("t3_cs.safetensors", device="cpu")
multilingual_model.t3.load_state_dict(t3_state)
multilingual_model.t3.to(device).eval()
czech_text = "Dobrý den, vítáme vás v našem testu syntézy řeči"
wav_czech = multilingual_model.generate(czech_text)
ta.save("test-cs.wav", wav_czech, multilingual_model.sr)
contact :
e-mail : cyprienoucortex@gmail.com
☕ Support
I trained this model from my own financial resources with the sole aim of offering it to the huggingface open source community.
This model has cost me a lot of money. If you find this checkpoint useful and would like to support my work, you can do it via Ko-fi:
