Fresh init

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+*.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
+*.mdl filter=lfs diff=lfs merge=lfs -text
+*.fst filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+token.txt
+models/

README.md

@@ -0,0 +1,12 @@
+---
+title: Vosk
+emoji: 🚀
+colorFrom: gray
+colorTo: gray
+sdk: gradio
+sdk_version: 5.44.1
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,54 @@
+import os
+import wave
+import gradio as gr
+from vosk import Model, KaldiRecognizer
+
+# 🔹 Load models once at startup
+# Download models from https://alphacephei.com/vosk/models and unzip them in ./models/
+models = {
+    "English (US)": Model("models/vosk-model-small-en-us-0.15"),
+    "English (Indian)": Model("models/vosk-model-small-en-in-0.4"),
+    "Hindi": Model("models/vosk-model-small-hi-in-0.22"),
+    "Telugu": Model("models/vosk-model-small-te-in-0.22")
+}
+
+def transcribe(audio_file, language):
+    if audio_file is None:
+        return "Please record or upload an audio file."
+
+    # Open audio
+    wf = wave.open(audio_file, "rb")
+
+    # Ensure format
+    if wf.getnchannels() != 1 or wf.getsampwidth() != 2 or wf.getframerate() != 16000:
+        return "Audio must be mono PCM16 at 16kHz. Please re-upload."
+
+    rec = KaldiRecognizer(models[language], wf.getframerate())
+
+    results = []
+    while True:
+        data = wf.readframes(4000)
+        if len(data) == 0:
+            break
+        if rec.AcceptWaveform(data):
+            results.append(rec.Result())
+    results.append(rec.FinalResult())
+
+    # Extract recognized text
+    text = " ".join([r for r in results])
+    return text
+
+# 🔹 Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## 🎙️ Multi-Language Speech-to-Text with Vosk")
+    with gr.Row():
+        audio_input = gr.Audio(sources=["microphone", "upload"], type="filepath")
+        lang_dropdown = gr.Dropdown(choices=list(models.keys()), value="English (US)", label="Language")
+    output = gr.Textbox(label="Transcription")
+
+    btn = gr.Button("Transcribe")
+    btn.click(fn=transcribe, inputs=[audio_input, lang_dropdown], outputs=output)
+
+# Launch app
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=int(os.environ.get("PORT", 7860)))

requirements.txt

@@ -0,0 +1,2 @@
+vosk
+gradio