first commit

.gitignore

@@ -0,0 +1,2 @@
+venv
+.env

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y git ffmpeg
+
+COPY . .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

functions/utils.py

@@ -0,0 +1,11 @@
+import soundfile as sf
+
+
+def getAudioDuration(filePath: str) -> float:
+    try:
+        data, samplerate = sf.read(filePath)
+        duration = len(data) / samplerate
+        return duration
+    except Exception as e:
+        print(f"Error getting audio duration: {e}")
+        return 0.0

language/saudi_arabe/ar_stt.py

@@ -0,0 +1,28 @@
+import base64, tempfile, os, torch
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
+from functions.utils import getAudioDuration
+
+MODEL_NAME = "openai/whisper-large-v3"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+model = AutoModelForSpeechSeq2Seq.from_pretrained(MODEL_NAME, torch_dtype=torch.float16).to(device)
+processor = AutoProcessor.from_pretrained(MODEL_NAME)
+pipe = pipeline("automatic-speech-recognition", model=model, tokenizer=processor.tokenizer,
+    feature_extractor=processor.feature_extractor, torch_dtype=torch.float16, device=device)
+
+
+def arSTT(audioBase64: str) -> dict:
+    audioBytes = base64.b64decode(audioBase64)
+
+    with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tempFile:
+        tempFile.write(audioBytes)
+        tempAudioPath = tempFile.name
+
+    try:
+        result = pipe(tempAudioPath, generate_kwargs={"language": "arabic"})
+        text = result["text"]
+        duration = getAudioDuration(tempAudioPath)
+    finally:
+        os.remove(tempAudioPath)
+
+    return {'text': text, 'language': 'ar', 'duration': duration}

language/saudi_arabe/ar_tts.py

@@ -0,0 +1,29 @@
+import torchaudio as ta, tempfile, base64, os, torch
+from huggingface_hub import snapshot_download
+from safetensors.torch import load_file as load_safetensors
+from chatterbox import mtl_tts
+
+MODEL_NAME = "NAMAA-Space/NAMAA-Saudi-TTS"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+ckpt_dir = snapshot_download(repo_id=MODEL_NAME)
+model = mtl_tts.ChatterboxMultilingualTTS.from_pretrained(device=device)
+t3_state = load_safetensors(f"{ckpt_dir}/t3_mtl23ls_v2.safetensors", device=device)
+model.t3.load_state_dict(t3_state)
+model.t3.to(device).eval()
+
+
+def arTTS(text: str) -> str:
+    with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tempFile:
+        tempAudioPath = tempFile.name
+
+    try:
+        wav = model.generate(text, language_id="ar")
+        ta.save(tempAudioPath, wav, model.sr)
+        
+        with open(tempAudioPath, "rb") as file:
+            audioBase64 = base64.b64encode(file.read()).decode("utf-8")
+    finally:
+        os.remove(tempAudioPath) 
+
+    return audioBase64

main.py

@@ -0,0 +1,49 @@
+from fastapi import FastAPI, Request, HTTPException
+
+from language.saudi_arabe.ar_stt import arSTT
+from language.saudi_arabe.ar_tts import arTTS
+
+import os
+from huggingface_hub import login
+login(token=os.environ["HF_TOKEN"])
+
+
+
+app = FastAPI(
+    version='1.0.0',
+    root_path='/api',
+)
+
+
+@app.post("/mms/speechToText")
+async def mmsSpeechToText(request: Request):
+    body: dict = await request.json()
+    try:
+        audioBase64 = body.get('audioBase64')
+        sourceLang = body.get('sourceLang')
+
+        if sourceLang == 'ar':
+            data = arSTT(audioBase64=audioBase64)
+            return data
+        else:
+            raise HTTPException(status_code=400, detail=f"STT error: Invalid sourceLang - {sourceLang}")
+    except Exception as e:
+        print(f"STT error: {e}")
+        raise HTTPException(status_code=400, detail=f"STT error: {e}")
+
+
+@app.post("/mms/textToSpeech")
+async def mmsTextToSpeech(request: Request):
+    body: dict = await request.json()
+    try:
+        text = body.get('text')
+        sourceLang = body.get('sourceLang')
+
+        if sourceLang == 'ar':
+            audioBase64 = arTTS(text=text)
+            return { 'audioBase64': audioBase64 }
+        else:
+            raise HTTPException(status_code=400, detail=f"STT error: Invalid sourceLang - {sourceLang}")
+    except Exception as e:
+        print(f"TTS error: {e}")
+        raise HTTPException(status_code=400, detail=f"TTS error: {e}")

requirements.txt

@@ -0,0 +1,129 @@
+absl-py==2.4.0
+aiofiles==24.1.0
+annotated-doc==0.0.4
+annotated-types==0.7.0
+antlr4-python3-runtime==4.9.3
+anyio==4.14.1
+audioread==3.1.0
+bitarray==3.8.2
+bitstring==4.4.0
+brotli==1.2.0
+catalogue==2.0.10
+certifi==2026.6.17
+cffi==2.0.0
+cfgv==3.5.0
+charset-normalizer==3.4.7
+chatterbox-tts @ git+https://github.com/resemble-ai/chatterbox.git@65b18437192794391a0308a8f705b1e33e633948
+click==8.4.2
+conformer==0.3.2
+contourpy==1.3.2
+cycler==0.12.1
+decorator==5.3.1
+Deprecated==1.3.1
+diffusers==0.29.0
+distlib==0.4.3
+einops==0.8.2
+exceptiongroup==1.3.1
+fastapi==0.138.1
+ffmpy==1.0.0
+filelock==3.29.4
+fonttools==4.63.0
+fsspec==2026.6.0
+gradio==6.8.0
+gradio_client==2.2.0
+groovy==0.1.2
+grpcio==1.81.1
+h11==0.16.0
+hf-xet==1.5.1
+httpcore==1.0.9
+httpx==0.28.1
+huggingface_hub==1.21.0
+identify==2.6.19
+idna==3.18
+importlib_metadata==9.0.0
+jaconv==0.5.0
+Jinja2==3.1.6
+joblib==1.5.3
+kiwisolver==1.5.0
+lazy-loader==0.5
+librosa==0.11.0
+llvmlite==0.47.0
+Markdown==3.10.2
+markdown-it-py==4.2.0
+MarkupSafe==3.0.3
+matplotlib==3.10.9
+mdurl==0.1.2
+ml_dtypes==0.5.4
+mpmath==1.3.0
+msgpack==1.2.1
+networkx==3.4.2
+nodeenv==1.10.0
+numba==0.65.1
+numpy==1.26.4
+omegaconf==2.3.1
+onnx==1.22.0
+orjson==3.11.9
+packaging==26.2
+pandas==2.3.3
+pillow==12.2.0
+platformdirs==4.10.0
+pooch==1.9.0
+praat-parselmouth==0.4.7
+pre_commit==4.6.0
+protobuf==7.35.1
+pycparser==3.0
+pydantic==2.13.4
+pydantic_core==2.46.4
+pydub==0.25.1
+Pygments==2.20.0
+pykakasi==2.3.0
+pyloudnorm==0.2.0
+pyparsing==3.3.2
+pyrubberband==0.4.0
+python-dateutil==2.9.0.post0
+python-discovery==1.4.2
+python-multipart==0.0.32
+pytz==2026.2
+PyWavelets==1.8.0
+PyYAML==6.0.3
+regex==2026.5.9
+requests==2.34.2
+# resemble-perth @ git+https://github.com/resemble-ai/Perth.git@ce86c49d029f42272c1902eccb675556b9ed2330
+rich==15.0.0
+s3tokenizer==0.3.0
+safehttpx==0.1.7
+safetensors==0.5.3
+scikit-learn==1.7.2
+scipy==1.15.3
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.17.0
+soundfile==0.14.0
+sox==1.5.0
+soxr==1.1.0
+spacy_pkuseg==1.0.1
+srsly==2.5.3
+starlette==0.52.1
+sympy==1.13.1
+tabulate==0.10.0
+tensorboard==2.20.0
+tensorboard-data-server==0.7.2
+threadpoolctl==3.6.0
+tibs==0.5.7
+tokenizers==0.22.2
+tomlkit==0.13.3
+torch==2.6.0
+torchaudio==2.6.0
+tqdm==4.68.3
+transformers==5.2.0
+typer==0.25.1
+typer-slim==0.24.0
+typing-inspection==0.4.2
+typing_extensions==4.15.0
+tzdata==2026.2
+urllib3==2.7.0
+uvicorn==0.49.0
+virtualenv==21.5.1
+Werkzeug==3.1.8
+wrapt==2.2.2
+zipp==4.1.0