Upload 11 files

.gitattributes

@@ -1,35 +1,35 @@
-*.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
+*.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

README.md

@@ -1,14 +1,14 @@
----
-title: TalkAI
-emoji: 🚀
-colorFrom: purple
-colorTo: indigo
-sdk: gradio
-sdk_version: 5.47.2
-app_file: app.py
-pinned: false
-license: mit
-short_description: Translation
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: TalkAI
+emoji: 🚀
+colorFrom: purple
+colorTo: indigo
+sdk: gradio
+sdk_version: 5.47.2
+app_file: app.py
+pinned: false
+license: mit
+short_description: Translation
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,40 @@
+import gradio as gr
+from translator import Translator, CONFIG
+from tts_engine import TTSEngine
+
+translator = Translator(n2n_enabled=CONFIG["features"]["nigerian_to_nigerian_enabled"])
+tts_engine = TTSEngine(use_coqui=False)  # default: pyttsx3
+
+def translate_and_speak(input_text, input_lang, output_lang, use_coqui, clone_voice):
+    # Translate
+    translated = translator.translate(input_text, input_lang, output_lang)
+
+    # TTS
+    tts_engine.use_coqui = use_coqui
+    audio_path = tts_engine.speak(translated, lang=output_lang, voice_clone=clone_voice)
+
+    return translated, audio_path
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("## 🌍 Nigerian Voice Translator Assistant")
+
+    with gr.Row():
+        input_lang = gr.Dropdown(choices=["yoruba","hausa","igbo","pidgin","esan","tiv","calabar","benin"], value="yoruba", label="Input Language")
+        output_lang = gr.Dropdown(choices=["english","yoruba","hausa","igbo","pidgin","esan","tiv","calabar","benin"], value="english", label="Output Language")
+
+    input_text = gr.Textbox(label="Enter text")
+    use_coqui = gr.Checkbox(label="Use Coqui TTS (natural accents)", value=False)
+    clone_voice = gr.Checkbox(label="Clone my voice if available", value=False)
+
+    translate_btn = gr.Button("Translate & Speak")
+    output_text = gr.Textbox(label="Translation")
+    output_audio = gr.Audio(label="Spoken Output", type="filepath")
+
+    translate_btn.click(
+        fn=translate_and_speak,
+        inputs=[input_text, input_lang, output_lang, use_coqui, clone_voice],
+        outputs=[output_text, output_audio]
+    )
+
+demo.launch()

assistant.py

@@ -0,0 +1,38 @@
+import yaml
+from translation import Translator
+from tts_engine import TTSManager
+from speech_input import SpeechInput
+
+class VoiceTranslatorAssistant:
+    def __init__(self, config_file="config.yaml"):
+        with open(config_file, "r", encoding="utf-8") as f:
+            config = yaml.safe_load(f)
+
+        self.lang_a = config.get("default_language", "yoruba").lower()
+        self.lang_b = config.get("output_language", "english").lower()
+        self.n2n_enabled = config.get("features", {}).get("nigerian_to_nigerian_enabled", False)
+
+        self.translator = Translator(n2n_enabled=self.n2n_enabled)
+        self.tts = TTSManager(engine=config["speech"]["engine"], rate=config["speech"]["rate"], volume=config["speech"]["volume"])
+        self.speech = SpeechInput()
+
+    def run(self):
+        print(f"🌍 Two-Way Translator: {self.lang_a.upper()} ↔ {self.lang_b.upper()}")
+        while True:
+            # Speaker A
+            text_a = self.speech.listen(f"{self.lang_a.upper()} (Speaker A)")
+            if not text_a or text_a.lower() in ["quit", "exit", "stop"]:
+                break
+            trans_a = self.translator.translate(text_a, self.lang_a, self.lang_b)
+            print(f"👤 A said: {text_a}\n➡️ {trans_a}")
+            self.tts.speak(trans_a, lang=self.lang_b, speaker="B")
+
+            # Speaker B
+            text_b = self.speech.listen(f"{self.lang_b.upper()} (Speaker B)")
+            if not text_b or text_b.lower() in ["quit", "exit", "stop"]:
+                break
+            trans_b = self.translator.translate(text_b, self.lang_b, self.lang_a)
+            print(f"👤 B said: {text_b}\n➡️ {trans_b}")
+            self.tts.speak(trans_b, lang=self.lang_a, speaker="A")
+
+        print("👋 Session ended.")

config.yaml

@@ -0,0 +1,9 @@
+default_language: hausa
+output_language: english
+
+features:
+  nigerian_to_nigerian_enabled: true
+
+speech:
+  rate: 150
+  volume: 1.0

speech_input.py

@@ -0,0 +1,15 @@
+import speech_recognition as sr
+
+class SpeechInput:
+    def __init__(self):
+        self.recognizer = sr.Recognizer()
+
+    def listen(self, prompt="Speak/Type now..."):
+        print(f"\n[{prompt}] 🎙️ Listening...")
+        try:
+            with sr.Microphone() as source:
+                audio = self.recognizer.listen(source, timeout=5, phrase_time_limit=10)
+            return self.recognizer.recognize_google(audio)
+        except Exception:
+            # fallback: manual typing
+            return input(f"[{prompt}] (typing fallback): ")

translation.py

@@ -0,0 +1,81 @@
+import yaml
+from transformers import MarianMTModel, MarianTokenizer
+
+# ---------------- Load config ----------------
+CONFIG_FILE = "config.yaml"
+
+def load_config():
+    with open(CONFIG_FILE, "r", encoding="utf-8") as f:
+        return yaml.safe_load(f)
+
+CONFIG = load_config()
+
+# ---------------- Marian models ----------------
+MARIAN_MODELS = {
+    "yoruba": {
+        "to_en": "Helsinki-NLP/opus-mt-yo-en",
+        "to_lang": "Helsinki-NLP/opus-mt-en-yo"
+    },
+    "hausa": {
+        "to_en": "Helsinki-NLP/opus-mt-ha-en",
+        "to_lang": "Helsinki-NLP/opus-mt-en-ha"
+    },
+    "igbo": {
+        "to_en": "Helsinki-NLP/opus-mt-ig-en",
+        "to_lang": "Helsinki-NLP/opus-mt-en-ig"
+    },
+    "pidgin": {
+        "to_en": "Helsinki-NLP/opus-mt-pcm-en",
+        "to_lang": "Helsinki-NLP/opus-mt-en-pcm"
+    },
+}
+
+# ---------------- Fallback dictionary ----------------
+CUSTOM_DICT = {
+    "esan": {"Koyo": "Greetings", "Wa gié": "Come here"},
+    "tiv": {"M sugh u": "Good morning", "M gbee": "I am fine"},
+    "calabar": {"Nsidibe": "Welcome", "Abadie": "How are you?"},
+    "benin": {"Oba gha to kpere": "Long live the king", "Koyo": "Greetings"},
+    "pidgin": {
+        "How far": "How are you?",
+        "Wetin dey happen": "What’s going on?",
+        "Omo": "Kid / person (informal)",
+    },
+}
+
+
+class Translator:
+    def __init__(self, n2n_enabled=False):
+        self.n2n_enabled = n2n_enabled
+
+    def translate_with_marian(self, model_name, text):
+        tokenizer = MarianTokenizer.from_pretrained(model_name)
+        model = MarianMTModel.from_pretrained(model_name)
+        inputs = tokenizer(text, return_tensors="pt")
+        translated = model.generate(**inputs)
+        return tokenizer.decode(translated[0], skip_special_tokens=True)
+
+    def translate(self, text, input_lang, output_lang):
+        if not text.strip():
+            return ""
+
+        # ---- Marian supported ----
+        if input_lang in MARIAN_MODELS:
+            if output_lang == "english":
+                return self.translate_with_marian(MARIAN_MODELS[input_lang]["to_en"], text)
+            elif output_lang == input_lang:
+                return text
+            elif output_lang in MARIAN_MODELS:
+                if self.n2n_enabled:
+                    en_text = self.translate_with_marian(MARIAN_MODELS[input_lang]["to_en"], text)
+                    return self.translate_with_marian(MARIAN_MODELS[output_lang]["to_lang"], en_text)
+                else:
+                    return f"(🚧 Nigerian↔Nigerian to {output_lang} not enabled)"
+        # ---- Dictionary fallback ----
+        else:
+            if output_lang == "english":
+                return CUSTOM_DICT.get(input_lang, {}).get(text, text)
+            elif output_lang == input_lang:
+                return text
+            else:
+                return f"(⚠️ Dictionary doesn't support {input_lang}→{output_lang})"

tts_engine.py

@@ -0,0 +1,31 @@
+import os
+import pyttsx3
+from TTS.api import TTS
+
+class TTSEngine:
+    def __init__(self, use_coqui=False):
+        self.use_coqui = use_coqui
+        if self.use_coqui:
+            # Multilingual model (supports Yoruba/Hausa/Igbo accents)
+            self.tts = TTS("tts_models/multilingual/multi-dataset/your_tts", progress_bar=False, gpu=False)
+
+    def speak(self, text, lang="english", voice_clone=False):
+        """
+        Returns path to generated audio file (for Gradio playback).
+        """
+        if not text:
+            return None
+
+        out_file = "output.wav"
+
+        if self.use_coqui:
+            if voice_clone and os.path.exists("my_voice.wav"):
+                self.tts.tts_to_file(text=text, file_path=out_file, speaker_wav="my_voice.wav", language=lang)
+            else:
+                self.tts.tts_to_file(text=text, file_path=out_file, language=lang)
+        else:
+            engine = pyttsx3.init()
+            engine.save_to_file(text, out_file)
+            engine.runAndWait()
+
+        return out_file