Duplicate from Has-ai/text-speech

Co-authored-by: Hasmit Singla <[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 +1,13 @@
+---
+title: Text Speech
+emoji: 🏆
+colorFrom: yellow
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.29.0
+app_file: app.py
+pinned: false
+duplicated_from: Has-ai/text-speech
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,92 @@
+
+
+import logging
+from typing import cast
+
+import gradio as gr
+from balacoon_tts import TTS
+from huggingface_hub import hf_hub_download, list_repo_files
+
+
+# global tts module, initialized from a model selected
+tts = None
+
+
+def main():
+    logging.basicConfig(level=logging.INFO)
+
+    with gr.Blocks() as demo:
+        gr.Markdown(
+            """
+            <h1 align="center">Clone your voice</h1>
+
+            1. Write an utterance to generate,
+            2. Select the model to synthesize with
+            3. Select speaker
+            4. Hit "Generate" and listen to the result!
+
+            When you select model for the first time,
+            it will take a little time to download it.
+            """
+        )
+        with gr.Row(variant="panel"):
+            text = gr.Textbox(label="Text", placeholder="Type something here...")
+
+        with gr.Row():
+            with gr.Column(variant="panel"):
+                repo_files = list_repo_files(repo_id="balacoon/tts")
+                model_files = [x for x in repo_files if x.endswith("_cpu.addon")]
+                model_name = gr.Dropdown(
+                    label="Model",
+                    choices=model_files,
+                )
+            with gr.Column(variant="panel"):
+                speaker = gr.Dropdown(label="Speaker", choices=[])
+
+            def set_model(model_name_str: str):
+                """
+                gets value from `model_name`, loads model,
+                re-initializes tts object, gets list of
+                speakers that model supports and set them to `speaker`
+                """
+                model_path = hf_hub_download(
+                    repo_id="balacoon/tts", filename=model_name_str
+                )
+                global tts
+                tts = TTS(model_path)
+                speakers = tts.get_speakers()
+                value = speakers[-1]
+                return gr.Dropdown.update(
+                    choices=speakers, value=value, visible=True
+                )
+
+            model_name.change(set_model, inputs=model_name, outputs=speaker)
+
+        with gr.Row(variant="panel"):
+            generate = gr.Button("Generate")
+        with gr.Row(variant="panel"):
+            audio = gr.Audio()
+
+        def synthesize_audio(text_str: str, speaker_str: str = ""):
+            """
+            gets utterance to synthesize from `text` Textbox
+            and speaker name from `speaker` dropdown list.
+            speaker name might be empty for single-speaker models.
+            Synthesizes the waveform and updates `audio` with it.
+            """
+            if not text_str:
+                logging.info("text or speaker are not provided")
+                return None
+            global tts
+            if len(text_str) > 1024:
+                text_str = text_str[:1024]
+            samples = cast(TTS, tts).synthesize(text_str, speaker_str)
+            return gr.Audio.update(value=(cast(TTS, tts).get_sampling_rate(), samples))
+
+        generate.click(synthesize_audio, inputs=[text, speaker], outputs=audio)
+
+    demo.launch()
+
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,5 @@
+--index-url https://pypi.fury.io/balacoon/
+--extra-index-url https://pypi.org/simple/
+balacoon-tts==0.1.1
+huggingface_hub
+numpy

setup.cfg

@@ -0,0 +1,12 @@
+[flake8]
+max_complexity=10
+per-file-ignores=__init__.py:F401,F403
+ignore = E203,W503
+max-line-length=119
+
+[isort]
+profile=black
+line_length=119
+
+[mypy]
+ignore_missing_imports = True