Upload 56 files

unlimit gen.py

@@ -0,0 +1,257 @@
+from kokoro import KModel, KPipeline
+import gradio as gr
+import os
+import random
+import torch
+import logging
+import soundfile as sf
+
+# Optional: import Resemblyzer for voice cloning (install via pip install resemblyzer)
+try:
+    from resemblyzer import VoiceEncoder, preprocess_wav
+    encoder = VoiceEncoder()
+except ImportError:
+    encoder = None
+
+# Configuration
+VOICE_DIR = r"D:\New folder (2)\model\voices"
+OUTPUT_DIR = r"D:\New folder (2)\output_audio"
+TEXT = "Hello, this is a test of the Kokoro TTS system."
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Device setup
+CUDA_AVAILABLE = torch.cuda.is_available()
+device = "cuda" if CUDA_AVAILABLE else "cpu"
+logger.info(f"Using hardware: {device}")
+
+# Load models for CPU and GPU (if available)
+models = {gpu: KModel("hexgrad/Kokoro-82M").to("cuda" if gpu else "cpu").eval() for gpu in [False] + ([True] if CUDA_AVAILABLE else [])}
+
+# Define pipelines for American ('a') and British ('b') English
+pipelines = {
+    'a': KPipeline(model=models[False], lang_code='a', device='cpu'),  # American English
+    'b': KPipeline(model=models[False], lang_code='b', device='cpu')   # British English
+}
+
+# Set custom pronunciations for "kokoro" in both American and British modes
+try:
+    pipelines["a"].g2p.lexicon.golds["kokoro"] = "kˈOkəɹO"
+    pipelines["b"].g2p.lexicon.golds["kokoro"] = "kˈQkəɹQ"
+except AttributeError as e:
+    logger.warning(f"Could not set custom pronunciations: {e}")
+
+def forward_gpu(text, voice_path, speed):
+    # Use the GPU model directly without spaces.GPU decorator
+    pipeline = pipelines[voice_path[0]]
+    # Ensure the pipeline uses the GPU model
+    pipeline.model = models[True]  # Switch to GPU model
+    generator = pipeline(text, voice=voice_path, speed=speed)
+    for _, _, audio in generator:
+        return audio
+    return None
+
+def generate_first(text, voice="af_bella.pt", speed=1, use_gpu=CUDA_AVAILABLE, clone_voice_file=None):
+    voice_path = os.path.join(VOICE_DIR, voice)
+    if not os.path.exists(voice_path):
+        raise FileNotFoundError(f"Voice file not found: {voice_path}")
+
+    pipeline = pipelines[voice[0]]
+
+    # If a clone file is provided and the encoder is available, try to clone the voice
+    if clone_voice_file is not None and encoder is not None:
+        try:
+            # clone_voice_file is a file path (string) in Gradio with type="filepath"
+            wav = preprocess_wav(clone_voice_file)
+            cloned_voice = torch.tensor(encoder.embed_utterance(wav), device=device).unsqueeze(0)
+            temp_voice_path = os.path.join(VOICE_DIR, "cloned_voice.pt")
+            torch.save(cloned_voice, temp_voice_path)
+            voice_path = temp_voice_path
+        except Exception as e:
+            logger.error(f"Error cloning voice: {e}")
+            voice_path = os.path.join(VOICE_DIR, voice)
+
+    use_gpu = use_gpu and CUDA_AVAILABLE
+    try:
+        if use_gpu:
+            audio = forward_gpu(text, voice_path, speed)
+        else:
+            pipeline.model = models[False]  # Ensure CPU model is used
+            generator = pipeline(text, voice=voice_path, speed=speed)
+            for _, ps, audio in generator:
+                return (24000, audio.numpy()), ps
+    except gr.exceptions.Error as e:
+        if use_gpu:
+            gr.Warning(str(e))
+            gr.Info("Retrying with CPU. To avoid this error, change Hardware to CPU.")
+            pipeline.model = models[False]  # Switch to CPU model
+            generator = pipeline(text, voice=voice_path, speed=speed)
+            for _, ps, audio in generator:
+                return (24000, audio.numpy()), ps
+        else:
+            raise gr.Error(e)
+    return None, ""
+
+def predict(text, voice="af_bella.pt", speed=1):
+    return generate_first(text, voice, speed, use_gpu=False)[0]
+
+def tokenize_first(text, voice="af_bella.pt"):
+    voice_path = os.path.join(VOICE_DIR, voice)
+    if not os.path.exists(voice_path):
+        raise FileNotFoundError(f"Voice file not found: {voice_path}")
+
+    pipeline = pipelines[voice[0]]
+    generator = pipeline(text, voice=voice_path)
+    for _, ps, _ in generator:
+        return ps
+    return ""
+
+def generate_all(text, voice="af_bella.pt", speed=1, use_gpu=CUDA_AVAILABLE):
+    voice_path = os.path.join(VOICE_DIR, voice)
+    if not os.path.exists(voice_path):
+        raise FileNotFoundError(f"Voice file not found: {voice_path}")
+
+    pipeline = pipelines[voice[0]]
+    use_gpu = use_gpu and CUDA_AVAILABLE
+    first = True
+    if use_gpu:
+        pipeline.model = models[True]  # Switch to GPU model
+    else:
+        pipeline.model = models[False]  # Switch to CPU model
+    generator = pipeline(text, voice=voice_path, speed=speed)
+    for _, _, audio in generator:
+        yield 24000, audio.numpy()
+        if first:
+            first = False
+            yield 24000, torch.zeros(1).numpy()
+
+# Load random quotes and sample texts
+try:
+    with open("en.txt", "r") as r:
+        random_quotes = [line.strip() for line in r]
+except FileNotFoundError:
+    random_quotes = ["Hello, this is a test of the Kokoro TTS system."]
+
+def get_random_quote():
+    return random.choice(random_quotes)
+
+def get_gatsby():
+    try:
+        with open("gatsby5k.md", "r") as r:
+            return r.read().strip()
+    except FileNotFoundError:
+        return "The Great Gatsby text not found."
+
+def get_frankenstein():
+    try:
+        with open("frankenstein5k.md", "r") as r:
+            return r.read().strip()
+    except FileNotFoundError:
+        return "Frankenstein text not found."
+
+# Dynamically load all .pt voice files from VOICE_DIR
+def load_voice_choices():
+    voice_files = [f for f in os.listdir(VOICE_DIR) if f.endswith('.pt')]
+    choices = {}
+    for voice_file in voice_files:
+        # Determine the voice type based on the prefix
+        prefix = voice_file[:2]
+        if prefix == 'af':
+            label = f"🇺🇸 🚺 {voice_file[3:-3].capitalize()}"
+        elif prefix == 'am':
+            label = f"🇺🇸 🚹 {voice_file[3:-3].capitalize()}"
+        elif prefix == 'bf':
+            label = f"🇬🇧 🚺 {voice_file[3:-3].capitalize()}"
+        elif prefix == 'bm':
+            label = f"🇬🇧 🚹 {voice_file[3:-3].capitalize()}"
+        else:
+            label = f"Unknown {voice_file[:-3]}"
+        choices[label] = voice_file
+    return choices
+
+CHOICES = load_voice_choices()
+
+# Log available voices
+for label, voice_path in CHOICES.items():
+    full_path = os.path.join(VOICE_DIR, voice_path)
+    if not os.path.exists(full_path):
+        logger.warning(f"Voice file not found: {full_path}")
+    else:
+        logger.info(f"Loaded voice: {label} ({voice_path})")
+
+# If no voices are found, add a default fallback
+if not CHOICES:
+    logger.warning("No voice files found in VOICE_DIR. Adding a placeholder.")
+    CHOICES = {"🇺🇸 🚺 Bella 🔥": "af_bella.pt"}
+
+TOKEN_NOTE = '''
+💡 Customize pronunciation with Markdown link syntax and /slashes/ like [Kokoro](/kˈOkəɹO/)
+
+💬 To adjust intonation, try punctuation ;:,.!?—…"()“” or stress ˈ and ˌ
+
+⬇️ Lower stress [1 level](-1) or [2 levels](-2)
+
+⬆️ Raise stress 1 level [or](+2) 2 levels (only works on less stressed, usually short words)
+'''
+
+with gr.Blocks() as generate_tab:
+    out_audio = gr.Audio(label="Output Audio", interactive=False, streaming=False, autoplay=True)
+    generate_btn = gr.Button("Generate", variant="primary")
+    with gr.Accordion("Output Tokens", open=True):
+        out_ps = gr.Textbox(interactive=False, show_label=False,
+                            info="Tokens used to generate the audio, up to 510 context length.")
+        tokenize_btn = gr.Button("Tokenize", variant="secondary")
+        gr.Markdown(TOKEN_NOTE)
+        predict_btn = gr.Button("Predict", variant="secondary", visible=False)
+
+with gr.Blocks() as stream_tab:
+    out_stream = gr.Audio(label="Output Audio Stream", interactive=False, streaming=True, autoplay=True)
+    with gr.Row():
+        stream_btn = gr.Button("Stream", variant="primary")
+        stop_btn = gr.Button("Stop", variant="stop")
+    with gr.Accordion("Note", open=True):
+        gr.Markdown("⚠️ There is an unknown Gradio bug that might yield no audio the first time you click Stream.")
+        gr.DuplicateButton()
+
+API_OPEN = True
+with gr.Blocks() as app:
+    with gr.Row():
+        with gr.Column():
+            text = gr.Textbox(label="Input Text", info="Arbitrarily many characters supported")
+            with gr.Row():
+                voice = gr.Dropdown(list(CHOICES.items()), value="af_bella.pt" if "af_bella.pt" in CHOICES.values() else list(CHOICES.values())[0], label="Voice",
+                                    info="Quality and availability vary by language")
+                use_gpu = gr.Dropdown(
+                    [("GPU 🚀", True), ("CPU 🐌", False)],
+                    value=CUDA_AVAILABLE,
+                    label="Hardware",
+                    info="GPU is usually faster, but may require CUDA support",
+                    interactive=CUDA_AVAILABLE
+                )
+            speed = gr.Slider(minimum=0.5, maximum=2, value=1, step=0.1, label="Speed")
+            clone_voice_file = gr.File(label="Clone Voice Sample (Optional)", file_count="single", type="filepath")
+            random_btn = gr.Button("🎲 Random Quote 💬", variant="secondary")
+            with gr.Row():
+                gatsby_btn = gr.Button("🥂 Gatsby 📕", variant="secondary")
+                frankenstein_btn = gr.Button("💀 Frankenstein 📗", variant="secondary")
+        with gr.Column():
+            gr.TabbedInterface([generate_tab, stream_tab], ["Generate", "Stream"])
+    random_btn.click(fn=get_random_quote, inputs=[], outputs=[text])
+    gatsby_btn.click(fn=get_gatsby, inputs=[], outputs=[text])
+    frankenstein_btn.click(fn=get_frankenstein, inputs=[], outputs=[text])
+    generate_btn.click(fn=generate_first, inputs=[text, voice, speed, use_gpu, clone_voice_file],
+                       outputs=[out_audio, out_ps])
+    tokenize_btn.click(fn=tokenize_first, inputs=[text, voice], outputs=[out_ps])
+    stream_event = stream_btn.click(fn=generate_all, inputs=[text, voice, speed, use_gpu], outputs=[out_stream])
+    stop_btn.click(fn=None, cancels=[stream_event])
+    predict_btn.click(fn=predict, inputs=[text, voice, speed], outputs=[out_audio])
+
+if __name__ == "__main__":
+    app.queue(api_open=API_OPEN).launch(
+        server_name="127.0.0.1",
+        server_port=40001,
+        show_api=API_OPEN,
+        inbrowser=True
+    )

voices/af_alloy.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d877149dd8b348fbad12e5845b7e43d975390e9f3b68a811d1d86168bef5aa3
+size 523425

voices/af_aoede.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03bd1a4c3716c2d8eaa3d50022f62d5c31cfbd6e15933a00b17fefe13841cc4
+size 523425

voices/af_bella.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb64e02fcc8de0327a8e13817e49c76c945ecf0052ceac97d3081480e8e48d6
+size 523425

voices/af_heart.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ab5709b8ffab19bfd849cd11d98f75b60af7733253ad0d67b12382a102cb4ff
+size 523425

voices/af_jessica.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdfdccb8cc975aa34ee6b89642963b0064237675de0e41a30ae64cc958dd4e87
+size 523435

voices/af_kore.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bfbc512321c3db49dff984ac675fa5ac7eaed5a96cc31104d3a9080e179d69d
+size 523420

voices/af_nicole.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5561808bcf5250fe8c5f5de32caf2d94f27e57e95befdb098c5c85991d4c5da
+size 523430

voices/af_nova.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0233676ddc21908c37a1f102f6b88a59e4e5c1bd764983616eb9eda629dbcd2
+size 523420

voices/af_river.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e149459bd9c084416b74756b9bd3418256a8b839088abb07d463730c369dab8f
+size 523425

voices/af_sarah.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bd364ea3be9eb3e9685e8f9a15448c4883112a7c0ff7ab139fa4088b08cef9
+size 523425

voices/af_sky.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c799548aed06e0cb0d655a85a01b48e7f10484d71663f9a3045a5b9362e8512c
+size 523351

voices/am_adam.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced7e284aba12472891be1da3ab34db84cc05cc02b5889535796dbf2d8b0cb34
+size 523420

voices/am_echo.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bcfdc852bc985fb45c396c561e571ffb9183930071f962f1b50df5c97b161e8
+size 523420

voices/am_eric.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ada66f0eefff34ec921b1d7474d7ac8bec00cd863c170f1c534916e9b8212aae
+size 523420

voices/am_fenrir.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e507eca1db08230ae3b6232d59c10aec9630022d19accac4f5d12fcec3c37a
+size 523430

voices/am_liam.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c82550757ddb31308b97f30040dda8c2d609a9e2de6135848d0a948368138518
+size 523420

voices/am_michael.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a443b79a4b22489a5b0ab7c651a0bcd1a30bef675c28333f06971abbd47bd37
+size 523435

voices/am_onyx.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8452be16cd0f6da7b4579eaf7b1e4506e92524882053d86d72b96b9a7fed584
+size 523420

voices/am_puck.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1d8973f4ce4b7d8ae407c77a435f485dabc052081b80ea75c4f30b84f36223
+size 523420

voices/am_santa.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2f7582fa2b1f160e90aafe6d0b442a685e773608b6667e545d743b073e97a7
+size 523425

voices/bf_alice.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d292651b6af6c0d81705c2580dcb4463fccc0ff7b8d618a471dbb4e45655b3f3
+size 523425

voices/bf_emma.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a423deabf4a52b4f49318c51742c54e21bb89bbbe9a12141e7758ddb5da701
+size 523420

voices/bf_isabella.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdd4c37003805104d1d08fb1e05855c8fb2c68de24ca6e71f264a30aaa59eefd
+size 523440

voices/bf_lily.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e09c2e481e2d53004d7e5ae7d3a325369e130a6f45c35a6002de75084be9285
+size 523420

voices/bm_daniel.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc3fce4e9c12ed4dbc8fa9680cfe51ee190a96444ce7c3ad647549a30823fc5d
+size 523430

voices/bm_fable.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d44935f3135257a9064df99f007fc1342ff1aa767552b4a4fa4c3b2e6e59079c
+size 523425

voices/bm_george.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1bc812213dc59774769e5c80004b13eeb79bd78130b11b2d7f934542dab811b
+size 523430

voices/bm_lewis.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5204750dcba01029d2ac9cec17aec3b20a6d64073c579d694a23cb40effbd0e
+size 523425

voices/ef_dora.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d69b0f8a2b87a345f269d89639f89dfbd1a6c9da0c498ae36dd34afcf35530
+size 523420

voices/em_alex.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eac53f767c3f31a081918ba531969aea850bed18fe56419b804d642c6973431
+size 523420

voices/em_santa.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa8620cb96cec705823efca0d956a63e158e09ad41aca934d354b7f0778f63cb
+size 523430

voices/ff_siwis.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8073bf2d2c4b9543a90f2f0fd2144de4ed157e2d4b79ddeb0d5123066171fbc9
+size 523425

voices/hf_alpha.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06906fe05746d13a79c5c01e21fd7233b05027221a933c9ada650f5aafc8f044
+size 523425

voices/hf_beta.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c0a1a6272e98d43f4511bba40e30dd9c8ceaf5f39af869509b9f51a71c503e
+size 523420

voices/hm_omega.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b55f02a8e8483fffe0afa566e7d22ed8013acf47ad4f6bbee2795a840155703e
+size 523425

voices/hm_psi.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0f055cea4f1083f4ef127ece48d71606347f6557dbb961c0ca5740a2da485b
+size 523351

voices/if_sara.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c0b253b955fe32f1a1a86006aebe83d050ea95afd0e7be15182f087deedbf55
+size 523425

voices/im_nicola.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:234ed06648649f9bd874b37508ea17560b9c993ef85b4ddb3e3a71e062bd2c12
+size 523341

voices/jf_alpha.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bf4c9dc69e45ee46183b071f4db766349aac5592acbcfeaf051018048a5d787
+size 523425

voices/jf_gongitsune.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b171917f18f351e65f2bf9657700cd6bfec4e65589c297525b9cf3c20105770
+size 523351

voices/jf_nezumi.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d83f007a7f01783b77014561a7d493d327a0210e143440e91c9b697590d27661
+size 523420

voices/jf_tebukuro.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d6917904438aec85f73a6fa1f7ac2be6481aae47c697834936930a91796c576
+size 523435

voices/jm_kumo.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98340afd68b1cee84fe0cd95528cfa6d4b39e416aa75a9df64049d52c8b55896
+size 523425

voices/pf_dora.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07e4ff987c5d5a8c3995efd15cc4f0db7c4c15e881b198d8ab7f67ecf51f5eb7
+size 523425

voices/pm_alex.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf0ba8c573c2480fc54123683a35cf1e2ae130428e441eb91f9149bdb188a526
+size 523425

voices/pm_santa.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42103169c5c872abbafb9129133af7e942bb9d272c3cc3b95c203e7d7198c29
+size 523430

voices/zf_xiaobei.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b76be63dab4f4f96962030acc0126a9aee9728608fbbe115e2b58a2bd504df6
+size 523435

voices/zf_xiaoni.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b49f169bf1640f4f43c25e13daa39f7b98d15d00823e83ef5c14b3ced59e49
+size 523430