import os import spaces os.system("git clone --branch v3.1 https://github.com/DigitalPhonetics/IMS-Toucan.git toucan_codebase") os.system("mv toucan_codebase/* .") from run_model_downloader import download_models download_models() import gradio as gr import torch.cuda from Preprocessing.multilinguality.SimilaritySolver import load_json_from_path from Utility.utils import float2pcm import os import torch from Architectures.ControllabilityGAN.GAN import GanWrapper from InferenceInterfaces.ToucanTTSInterface import ToucanTTSInterface from Utility.storage_config import MODELS_DIR class ControllableInterface(torch.nn.Module): def __init__(self, available_artificial_voices=1000): super().__init__() self.model = ToucanTTSInterface(device="cpu", tts_model_path="Meta") self.wgan = GanWrapper(os.path.join(MODELS_DIR, "Embedding", "embedding_gan.pt"), device="cpu") self.generated_speaker_embeds = list() self.available_artificial_voices = available_artificial_voices self.current_language = "" self.current_accent = "" def read(self, prompt, language, accent, voice_seed, prosody_creativity, duration_scaling_factor, pause_duration_scaling_factor, pitch_variance_scale, energy_variance_scale, emb_slider_1, emb_slider_2, emb_slider_3, emb_slider_4, emb_slider_5, emb_slider_6, loudness_in_db ): if self.current_language != language: self.model.set_phonemizer_language(language) self.current_language = language if self.current_accent != accent: self.model.set_accent_language(accent) self.current_accent = accent self.wgan.set_latent(voice_seed) controllability_vector = torch.tensor([emb_slider_1, emb_slider_2, emb_slider_3, emb_slider_4, emb_slider_5, emb_slider_6], dtype=torch.float32) embedding = self.wgan.modify_embed(controllability_vector) self.model.set_utterance_embedding(embedding=embedding) phones = self.model.text2phone.get_phone_string(prompt) if len(phones) > 1800: if language == "deu": prompt = "Deine Eingabe war zu lang. Bitte versuche es entweder mit einem kürzeren Text oder teile ihn in mehrere Teile auf." elif language == "ell": prompt = "Η εισήγησή σας ήταν πολύ μεγάλη. Παρακαλώ δοκιμάστε είτε ένα μικρότερο κείμενο είτε χωρίστε το σε διάφορα μέρη." elif language == "spa": prompt = "Su entrada es demasiado larga. Por favor, intente un texto más corto o divídalo en varias partes." elif language == "fin": prompt = "Vastauksesi oli liian pitkä. Kokeile joko lyhyempää tekstiä tai jaa se useampaan osaan." elif language == "rus": prompt = "Ваш текст слишком длинный. Пожалуйста, попробуйте либо сократить текст, либо разделить его на несколько частей." elif language == "hun": prompt = "Túl hosszú volt a bevitele. Kérjük, próbáljon meg rövidebb szöveget írni, vagy ossza több részre." elif language == "nld": prompt = "Uw input was te lang. Probeer een kortere tekst of splits het in verschillende delen." elif language == "fra": prompt = "Votre saisie était trop longue. Veuillez essayer un texte plus court ou le diviser en plusieurs parties." elif language == 'pol': prompt = "Twój wpis był zbyt długi. Spróbuj skrócić tekst lub podzielić go na kilka części." elif language == 'por': prompt = "O seu contributo foi demasiado longo. Por favor, tente um texto mais curto ou divida-o em várias partes." elif language == 'ita': prompt = "Il tuo input era troppo lungo. Per favore, prova un testo più corto o dividilo in più parti." elif language == 'cmn': prompt = "你的输入太长了。请尝试使用较短的文本或将其拆分为多个部分。" elif language == 'vie': prompt = "Đầu vào của bạn quá dài. Vui lòng thử một văn bản ngắn hơn hoặc chia nó thành nhiều phần." else: prompt = "Your input was too long. Please try either a shorter text or split it into several parts." if self.current_language != "eng": self.model.set_phonemizer_language("eng") self.current_language = "eng" if self.current_accent != "eng": self.model.set_accent_language("eng") self.current_accent = "eng" print(prompt) wav, sr, fig = self.model(prompt, input_is_phones=False, duration_scaling_factor=duration_scaling_factor, pitch_variance_scale=pitch_variance_scale, energy_variance_scale=energy_variance_scale, pause_duration_scaling_factor=pause_duration_scaling_factor, return_plot_as_filepath=True, prosody_creativity=prosody_creativity, loudness_in_db=loudness_in_db) return sr, wav, fig title = "Controllable Text-to-Speech for over 7000 Languages" article = "Check out the IMS Toucan TTS Toolkit at https://github.com/DigitalPhonetics/IMS-Toucan" available_artificial_voices = 1000 path_to_iso_list = "Preprocessing/multilinguality/iso_to_fullname.json" iso_to_name = load_json_from_path(path_to_iso_list) text_selection = [f"{iso_to_name[iso_code]} Text ({iso_code})" for iso_code in iso_to_name] controllable_ui = ControllableInterface(available_artificial_voices=available_artificial_voices) @spaces.GPU def read(prompt, language, voice_seed, prosody_creativity, duration_scaling_factor, pitch_variance_scale, energy_variance_scale, emb1, emb2 ): if torch.cuda.is_available(): controllable_ui.to("cuda") controllable_ui.device = "cuda" try: sr, wav, fig = controllable_ui.read(prompt, language.split(" ")[-1].split("(")[1].split(")")[0], language.split(" ")[-1].split("(")[1].split(")")[0], voice_seed, prosody_creativity, duration_scaling_factor, 1., pitch_variance_scale, energy_variance_scale, emb1, emb2, 0., 0., 0., 0., -24.) finally: controllable_ui.to("cpu") controllable_ui.device = "cpu" return (sr, float2pcm(wav)), fig iface = gr.Interface(fn=read, inputs=[gr.Textbox(lines=2, placeholder="write what you want the synthesis to read here...", value="The woods are lovely, dark and deep, but I have promises to keep, and miles to go, before I sleep.", label="Text input"), gr.Dropdown(text_selection, type="value", value='English Text (eng)', label="Select the Language of the Text (type on your keyboard to find it quickly)"), gr.Slider(minimum=0, maximum=available_artificial_voices, step=1, value=279, label="Random Seed for the artificial Voice"), gr.Slider(minimum=0.0, maximum=0.8, step=0.1, value=0.7, label="Prosody Creativity"), gr.Slider(minimum=0.7, maximum=1.3, step=0.1, value=1.0, label="Duration Scale"), gr.Slider(minimum=0.5, maximum=1.5, step=0.1, value=1.0, label="Pitch Variance Scale"), gr.Slider(minimum=0.5, maximum=1.5, step=0.1, value=1.0, label="Energy Variance Scale"), gr.Slider(minimum=-10.0, maximum=10.0, step=0.1, value=0.0, label="Femininity / Masculinity"), gr.Slider(minimum=-10.0, maximum=10.0, step=0.1, value=0.0, label="Voice Depth") ], outputs=[gr.Audio(type="numpy", label="Speech"), gr.Image(label="Visualization")], title=title, theme="default", allow_flagging="never", article=article) iface.launch()