Duplicate from jhlfrfufyfn/bel-tts

Co-authored-by: Nik <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Bel Tts
+emoji: 📚
+colorFrom: gray
+colorTo: gray
+sdk: gradio
+sdk_version: 3.13.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: jhlfrfufyfn/bel-tts
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,87 @@
+from TTS.utils.synthesizer import Synthesizer
+from huggingface_hub import hf_hub_download
+import gradio as gr
+import tempfile
+import os 
+
+REPO_ID = "jhlfrfufyfn/bel-tts"
+
+my_title = "Беларускі тэкст-у-маўленне"
+my_description = "Беларускамоўная мадэль для агучвання тэксту (травень 2023)."
+
+be_text = "Гепарды жывуць у адкрытых і прасторных месцах, дзе ёсць шмат здабычы."
+
+my_inputs = [
+  gr.inputs.Textbox(lines=5, label="Input Text", default=be_text),
+]
+
+my_outputs = gr.outputs.Audio(type="file", label="Output Audio")
+
+def belarusify_russian_text(text: str):
+    text = text.replace("и", "і")
+    text = text.replace("іу", "іў")
+    text = text.replace("оу", "оў")
+    text = text.replace("ау", "аў")
+    text = text.replace("ыу", "ыў")
+    text = text.replace("уу", "уў")
+    text = text.replace("юу", "юў")
+    text = text.replace("еу", "еў")
+    text = text.replace("ёу", "ёў")
+    text = text.replace("щ", "шч")
+    return text
+    
+import requests
+def tts(text: str):
+    print("Original text: ", text)
+    text = belarusify_russian_text(text)
+    print("Belarusified text: ", text)
+     # Sending a request to the fonemizer
+    headers = {'Content-Type': 'text/plain; charset=utf-8'}  # Specify the charset as UTF-8
+
+    response = requests.post("http://fonemizer.nikuchin.fun/processText", 
+                         data=text.encode('utf-8'),  # Encode the text as UTF-8
+                         headers=headers)
+
+    if response.status_code != 200:
+        raise Exception(f"Request to fonemizer failed with status code {response.status_code}")
+    print(response.content)
+    print(response.headers.get('Content-Type'))
+    text = response.text
+    best_model_path = hf_hub_download(repo_id=REPO_ID, filename="model.pth") 
+    config_path = hf_hub_download(repo_id=REPO_ID, filename="config.json")
+    vocoder_path = hf_hub_download(repo_id=REPO_ID, filename="vocoder.pth")
+    scale_stats_path = hf_hub_download(repo_id=REPO_ID, filename="scale_stats.npy")
+    vocoder_config_path = hf_hub_download(repo_id=REPO_ID, filename="vocoder_config.json")
+    
+    # init synthesizer  
+    synthesizer = Synthesizer(
+        best_model_path,
+        config_path,
+        None,
+        None,
+        vocoder_path,
+        vocoder_config_path,
+        None,
+        None,
+        False
+    )
+
+    # create audio file
+    wavs = synthesizer.tts(text)
+    with tempfile.NamedTemporaryFile(suffix = ".wav", delete = False) as fp:
+        synthesizer.save_wav(wavs, fp)                      
+    return fp.name 
+
+print("CWD IS ", os.getcwd())
+print("LIST IS", os.listdir())
+iface = gr.Interface(
+    fn=tts, 
+    inputs=my_inputs, 
+    outputs=my_outputs, 
+    title=my_title, 
+    description = my_description, 
+    article = "",
+    examples = "", 
+    allow_flagging=False
+)
+iface.launch()

requirements.txt

@@ -0,0 +1,2 @@
+gradio
+TTS==0.13.3

scale_stats.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b9cf60d8d5fc0a5efe55763250ccaa87e4e078ae8927508cd1b4b7ad8ccca3
+size 10790