dwani 0.1.0__py3-none-any.whl → 0.1.2__py3-none-any.whl

dwani/__init__.py

@@ -0,0 +1,39 @@
+from .client import DhwaniClient
+from .chat import Chat
+from .audio import Audio
+from .vision import Vision
+from .asr import ASR
+from .exceptions import DhwaniAPIError
+
+__all__ = ["DhwaniClient", "Chat", "Audio", "Vision", "ASR", "DhwaniAPIError"]
+
+# Optionally, instantiate a default client for convenience
+api_key = None
+api_base = "http://localhost:7860"
+
+def _get_client():
+    global _client
+    if "_client" not in globals() or _client is None:
+        from .client import DhwaniClient
+        globals()["_client"] = DhwaniClient(api_key=api_key, api_base=api_base)
+    return globals()["_client"]
+
+class chat:
+    @staticmethod
+    def create(prompt, **kwargs):
+        return _get_client().chat(prompt, **kwargs)
+
+class audio:
+    @staticmethod
+    def speech(*args, **kwargs):
+        return _get_client().speech(*args, **kwargs)
+
+class vision:
+    @staticmethod
+    def caption(*args, **kwargs):
+        return _get_client().caption(*args, **kwargs)
+
+class asr:
+    @staticmethod
+    def transcribe(*args, **kwargs):
+        return _get_client().transcribe(*args, **kwargs)

dwani/asr.py

@@ -0,0 +1,37 @@
+from .exceptions import DhwaniAPIError
+import requests
+def asr_transcribe(client, file_path, language):
+    with open(file_path, "rb") as f:
+        files = {"file": f}
+        resp = requests.post(
+            f"{client.api_base}/transcribe/?language={language}",
+            headers=client._headers(),
+            files=files
+        )
+    if resp.status_code != 200:
+        raise DhwaniAPIError(resp)
+    return resp.json()
+
+class ASR:
+    @staticmethod
+    def transcribe(*args, **kwargs):
+        from . import _get_client
+        return _get_client().transcribe(*args, **kwargs)
+
+
+'''
+from .docs import Documents
+
+class documents:
+    @staticmethod
+    def ocr(file_path, language=None):
+        return _get_client().document_ocr(file_path, language)
+
+    @staticmethod
+    def translate(file_path, src_lang, tgt_lang):
+        return _get_client().document_translate(file_path, src_lang, tgt_lang)
+
+    @staticmethod
+    def summarize(file_path, language=None):
+        return _get_client().document_summarize(file_path, language)
+'''

dwani/audio.py

@@ -0,0 +1,29 @@
+from .exceptions import DhwaniAPIError
+import requests
+def audio_speech(client, input, voice, model, response_format="mp3", output_file=None):
+    data = {
+        "input": input,
+        "voice": voice,
+        "model": model,
+        "response_format": response_format
+    }
+    resp = requests.post(
+        f"{client.api_base}/v1/audio/speech",
+        headers={**client._headers(), "Content-Type": "application/json"},
+        json=data,
+        stream=True
+    )
+    if resp.status_code != 200:
+        raise DhwaniAPIError(resp)
+    if output_file:
+        with open(output_file, "wb") as f:
+            for chunk in resp.iter_content(chunk_size=8192):
+                f.write(chunk)
+        return output_file
+    return resp.content
+
+class Audio:
+    @staticmethod
+    def speech(*args, **kwargs):
+        from . import _get_client
+        return _get_client().speech(*args, **kwargs)

dwani/chat.py

@@ -0,0 +1,17 @@
+from .exceptions import DhwaniAPIError
+import requests
+def chat_create(client, prompt, **kwargs):
+    resp = requests.post(
+        f"{client.api_base}/chat",
+        headers={**client._headers(), "Content-Type": "application/json"},
+        json={"prompt": prompt, **kwargs}
+    )
+    if resp.status_code != 200:
+        raise DhwaniAPIError(resp)
+    return resp.json()
+
+class Chat:
+    @staticmethod
+    def create(prompt, **kwargs):
+        from . import _get_client
+        return _get_client().chat(prompt, **kwargs)

dwani/client.py

@@ -0,0 +1,42 @@
+import os
+import requests
+from .exceptions import DhwaniAPIError
+
+class DhwaniClient:
+    def __init__(self, api_key=None, api_base=None):
+        self.api_key = api_key or os.getenv("DHWANI_API_KEY")
+        self.api_base = "https://dwani-dwani-server-workshop.hf.space"
+        #self.api_base = api_base or os.getenv("DHWANI_API_BASE", "http://localhost:7860")
+        if not self.api_key:
+            raise ValueError("DHWANI_API_KEY not set")
+
+    def _headers(self):
+        return {"X-API-Key": self.api_key}
+
+    def chat(self, prompt, **kwargs):
+        from .chat import chat_create
+        return chat_create(self, prompt, **kwargs)
+
+    def speech(self, *args, **kwargs):
+        from .audio import audio_speech
+        return audio_speech(self, *args, **kwargs)
+
+    def caption(self, *args, **kwargs):
+        from .vision import vision_caption
+        return vision_caption(self, *args, **kwargs)
+
+    def transcribe(self, *args, **kwargs):
+        from .asr import asr_transcribe
+        return asr_transcribe(self, *args, **kwargs)
+    def document_ocr(self, file_path, language=None):
+        from .docs import document_ocr
+        return document_ocr(self, file_path, language)
+
+    def document_translate(self, file_path, src_lang, tgt_lang):
+        from .docs import document_translate
+        return document_translate(self, file_path, src_lang, tgt_lang)
+
+    def document_summarize(self, file_path, language=None):
+        from .docs import document_summarize
+        return document_summarize(self, file_path, language)
+

dwani/docs.py

@@ -0,0 +1,70 @@
+import requests
+from .exceptions import DhwaniAPIError
+
+def document_ocr(client, file_path, language=None):
+    """OCR a document (image/PDF) and return extracted text."""
+    with open(file_path, "rb") as f:
+        files = {"file": f}
+        data = {}
+        if language:
+            data["language"] = language
+        resp = requests.post(
+            f"{client.api_base}/v1/document/ocr",
+            headers=client._headers(),
+            files=files,
+            data=data
+        )
+    if resp.status_code != 200:
+        raise DhwaniAPIError(resp)
+    return resp.json()
+
+def document_translate(client, file_path, src_lang, tgt_lang):
+    """Translate a document (image/PDF with text) from src_lang to tgt_lang."""
+    with open(file_path, "rb") as f:
+        files = {"file": f}
+        data = {
+            "src_lang": src_lang,
+            "tgt_lang": tgt_lang
+        }
+        resp = requests.post(
+            f"{client.api_base}/v1/document/translate",
+            headers=client._headers(),
+            files=files,
+            data=data
+        )
+    if resp.status_code != 200:
+        raise DhwaniAPIError(resp)
+    return resp.json()
+
+def document_summarize(client, file_path, language=None):
+    """Summarize a document (image/PDF/text)."""
+    with open(file_path, "rb") as f:
+        files = {"file": f}
+        data = {}
+        if language:
+            data["language"] = language
+        resp = requests.post(
+            f"{client.api_base}/v1/document/summarize",
+            headers=client._headers(),
+            files=files,
+            data=data
+        )
+    if resp.status_code != 200:
+        raise DhwaniAPIError(resp)
+    return resp.json()
+
+class Documents:
+    @staticmethod
+    def ocr(file_path, language=None):
+        from . import _get_client
+        return _get_client().document_ocr(file_path, language)
+
+    @staticmethod
+    def translate(file_path, src_lang, tgt_lang):
+        from . import _get_client
+        return _get_client().document_translate(file_path, src_lang, tgt_lang)
+
+    @staticmethod
+    def summarize(file_path, language=None):
+        from . import _get_client
+        return _get_client().document_summarize(file_path, language)

dwani/vision.py

@@ -0,0 +1,21 @@
+from .exceptions import DhwaniAPIError
+import requests
+def vision_caption(client, file_path, length="short"):
+    with open(file_path, "rb") as f:
+        files = {"file": f}
+        data = {"length": length}
+        resp = requests.post(
+            f"{client.api_base}/caption/",
+            headers=client._headers(),
+            files=files,
+            data=data
+        )
+    if resp.status_code != 200:
+        raise DhwaniAPIError(resp)
+    return resp.json()
+
+class Vision:
+    @staticmethod
+    def caption(*args, **kwargs):
+        from . import _get_client
+        return _get_client().caption(*args, **kwargs)

dwani-0.1.2.dist-info/METADATA

@@ -0,0 +1,188 @@
+Metadata-Version: 2.4
+Name: dwani
+Version: 0.1.2
+Summary: Multimodal AI server for Indian languages (speech, vision, LLMs, TTS, ASR, etc.)
+Author-email: sachin <python@dwani.ai>
+License: MIT License
+        
+        Copyright (c) 2025 Sachin Shetty
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Project-URL: Homepage, https://github.com/dwani-ai/dwani-server
+Project-URL: Source, https://github.com/dwani-ai/dwani-server
+Project-URL: Issues, https://github.com/dwani-ai/dwani-server/issues
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests>=2.25.0
+Dynamic: license-file
+
+# Dhwani Server
+
+Dhwani API is a FastAPI-based application providing AI-powered services for Indian languages, including text-to-speech (TTS), language model (LLM) chat, vision-language model (VLM) capabilities, and automatic speech recognition (ASR). It supports lazy loading of models for fast startup and includes endpoints for various tasks.
+
+## Features
+- **Text-to-Speech (TTS)**: Generate audio from text in Indian languages using Parler TTS.
+- **Chat**: Process Kannada prompts and respond in Kannada via translation and LLM.
+- **Vision-Language Model (VLM)**: Caption images, answer visual queries, detect, and point objects.
+- **Automatic Speech Recognition (ASR)**: Transcribe audio files in multiple Indian languages.
+- **Lazy Loading**: Models load on-demand or via an explicit endpoint for fast startup.
+
+## Prerequisites
+- **System Requirements - User **:
+    - **Python**: 3.10
+    - Ubuntu 22.04
+    - git 
+    - vscode
+- **System Requirements - Server **:
+  - Ubuntu with sufficient RAM (16GB+ recommended for models).
+  - Optional: NVIDIA GPU with CUDA support for faster inference.
+- **FFmpeg**: Required for audio processing (ASR).
+
+- Server Setup
+```bash
+export HF_HOME=/home/ubuntu/data-dhwani-models
+export HF_TOKEN='YOur-HF-token'
+python src/server/main.py --host 0.0.0.0 --port 7860 --config config_two
+```
+## Installation
+
+1. **Clone the Repository**:
+   ```bash
+   git clone https://github.com/slabstech/dhwani-server
+   cd dhwani-server
+   ```
+
+2. Install Libraries:
+    - On Ubuntu: ```sudo apt-get install ffmpeg build-essential```
+
+3. Set Up Virtual Environment:
+    ```bash
+    python -m venv venv
+    source venv/bin/activate 
+    ```
+4. Install Dependencies:
+    ```bash
+    sudo apt-get install -y ffmpeg build-essential
+    curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --no-modify-path --profile minimal
+    . "$HOME/.cargo/env"
+    export CC=/usr/bin/gcc
+    export ENV CXX=/usr/bin/g++
+    ```
+    ```bash
+    pip install --no-cache-dir --upgrade pip setuptools psutil setuptools-rust torch==2.6.0
+    pip install --no-cache-dir flash-attn --no-build-isolation
+    ```
+
+    ```bash
+    pip install -r requirements.txt
+    ```
+    
+4. Set Environment Variable:
+    Create a .env file in the root directory and add your API key:
+    plaintext
+    ```bash
+    API_KEY=your_secret_key
+    ```
+
+5. Running the Server
+    - Start the Server:
+    ```bash
+        python src/server/main.py --host 0.0.0.0 --port 7860 --config config_two
+    ```
+
+    - The server starts with models loaded on start
+    - Access the interactive API docs at http://localhost:7860/docs.
+    
+    - (Optional) Load All Models:
+    Preload all models (LLM, Translation, TTS, VLM, ASR) with:
+    - 
+    ```bash
+    curl -X POST "http://localhost:7860/load_all_models" -H "X-API-Key: your_secret_key"
+    ```
+
+- Usage
+    - Endpoints
+        - All endpoints require the X-API-Key header with the value from your .env file.
+
+    -    Health Check: GET /health
+    ```bash
+        curl "http://localhost:7860/health"
+    ```
+    - Response: 
+        ```bash 
+        {"status": "healthy", "model": "Qwen/Qwen2.5-3B-Instruct"}
+        ```
+    
+    - Text-to-Speech: POST /v1/audio/speech
+    ```  bash
+    curl -X POST "http://localhost:7860/v1/audio/speech" -H "X-API-Key: your_secret_key" -H "Content-Type: application/json" -d '{"input": "ನಮಸ್ಕಾರ", "voice": "Female voice", "model": "ai4bharat/indic-parler-tts", "response_format": "mp3"}' --output speech.mp3
+    ```
+    - Chat: POST /chat
+    ``` bash
+        curl -X POST "http://localhost:7860/chat" -H "X-API-Key: your_secret_key" -H "Content-Type: application/json" -d '{"prompt": "ನೀವು ಹೇಗಿದ್ದೀರಿ?"}'
+    ```
+
+    - Response: 
+            ```{"response": "<Kannada response>"}```
+    - Image Captioning: POST /caption/
+    ```bash
+        curl -X POST "http://localhost:7860/caption/" -H "X-API-Key: your_secret_key" -F "file=@image.jpg" -F "length=short"
+    ```
+    - Response:``` {"caption": "<short caption>"}```
+    - Visual Query: POST /visual_query/
+    ```bash
+        curl -X POST "http://localhost:7860/visual_query/" -H "X-API-Key: your_secret_key" -F "file=@image.jpg" -F "query=What is this?"
+    ```
+    - Response: ```{"answer": "<answer>"}```
+    - Object Detection: POST /detect/
+    ```bash
+        curl -X POST "http://localhost:7860/detect/" -H "X-API-Key: your_secret_key" -F "file=@image.jpg" -F "object_type=face"
+    ```
+    - Response: ```{"objects": [<list of detected objects>]}```
+    - Object Pointing: POST /point/
+    ```bash
+
+        curl -X POST "http://localhost:7860/point/" -H "X-API-Key: your_secret_key" -F "file=@image.jpg" -F "object_type=person"
+    ```
+    - Response: ```{"points": [<list of points>]}```
+    - Transcription: POST /transcribe/
+    ```bash
+    curl -X POST "http://localhost:7860/transcribe/?language=kannada" -H "X-API-Key: your_secret_key" -F "file=@audio.wav"
+    ```
+    - Response: ```{"text": "<transcribed text>"}```
+    - Batch Transcription: POST /transcribe_batch/
+    ```bash
+    curl -X POST "http://localhost:7860/transcribe_batch/?language=kannada" -H "X-API-Key: your_secret_key" -F "files=@audio1.wav" -F "files=@audio2.mp3"
+    ```
+    - Response: ```{"transcriptions": ["<text1>", "<text2>"]}```
+
+- Notes
+    - Lazy Loading: Models load on first use or via /load_all_models. Expect a delay on the first request for each model type.
+    Supported Languages: ASR supports multiple Indian languages (e.g., kannada, hindi, tamil); see models/asr.py for the full list.
+    Logs: Check dhwani_api.log for detailed logs (rotated at 10MB, 5 backups).
+    Performance: Use a GPU with flash-attn installed for faster TTS and ASR inference.
+
+- Troubleshooting
+
+    - Module Errors: Ensure all dependencies are installed. Re-run pip install if needed.
+    FFmpeg Not Found: Install FFmpeg and ensure it’s in your PATH.
+    Permission Denied: Run with sudo if accessing restricted ports (e.g., < 1024).
+

dwani-0.1.2.dist-info/RECORD

@@ -0,0 +1,13 @@
+dwani/__init__.py,sha256=P2pyHkZ7JHn6lHSEbCdV4hjYAwCOXHN3RbsNIU0F5PE,1084
+dwani/asr.py,sha256=Xe62t8dNQy9gRkn4LyjaagOXjKZ90aexYEL2D-oVP2U,1042
+dwani/audio.py,sha256=lyFjYAv4EsDIHPbopv9Lf5LJIzuJEuoBO9H37TVGaUo,894
+dwani/chat.py,sha256=xPfsWUmovkBfNdV1BWzVRPfvVM8sxAaaxMopq1OK7JE,523
+dwani/client.py,sha256=t2Gzik9S8De3-3CHY2IdmwJTxkIEmqQZHoiGkkga7fQ,1546
+dwani/docs.py,sha256=2B87KqshPl7-2gDJAJxdvcgmPWuC2IQ1FcsDIyeVJPg,2202
+dwani/exceptions.py,sha256=qEN5ukqlnN7v-kHNEnISWFMpPMt6uTft9mPsTXJ4LVA,227
+dwani/vision.py,sha256=xi9gVsL8MA8VQYXIV99uqKuxYfs1kWu4tvqzbe95F1Y,623
+dwani-0.1.2.dist-info/licenses/LICENSE,sha256=IAD8tbwWZbPWHXgYjabHoMv0aaUzZUYzYiEbfhTCisY,1070
+dwani-0.1.2.dist-info/METADATA,sha256=1VTsA00s9_Vzsm77wbbx6NYXi7p4kkWjiDIV0cVo7II,7765
+dwani-0.1.2.dist-info/WHEEL,sha256=DnLRTWE75wApRYVsjgc6wsVswC54sMSJhAEd4xhDpBk,91
+dwani-0.1.2.dist-info/top_level.txt,sha256=AM5EhkyuO_EXQFR9JIxEV6tAYMCCyc-a1dLifpCGBUk,6
+dwani-0.1.2.dist-info/RECORD,,

{dwani-0.1.0.dist-info → dwani-0.1.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.3.1)
+Generator: setuptools (80.4.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

dwani-0.1.2.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Sachin Shetty
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

dwani-0.1.2.dist-info/top_level.txt

@@ -0,0 +1 @@
+dwani

__init__.py

@@ -1,44 +0,0 @@
-from .client import DhwaniClient
-
-api_key = None
-api_base = "http://localhost:7860"
-
-_client = None
-
-def _get_client():
-    global _client
-    if _client is None:
-        _client = DhwaniClient(api_key=api_key, api_base=api_base)
-    return _client
-
-class Chat:
-    @staticmethod
-    def create(prompt):
-        return _get_client().chat(prompt)
-
-class Audio:
-    @staticmethod
-    def speech(input, voice, model, response_format="mp3", output_file=None):
-        return _get_client().speech(input, voice, model, response_format, output_file)
-
-class Vision:
-    @staticmethod
-    def caption(file_path, length="short"):
-        return _get_client().caption(file_path, length)
-    @staticmethod
-    def visual_query(file_path, query):
-        return _get_client().visual_query(file_path, query)
-    @staticmethod
-    def detect(file_path, object_type):
-        return _get_client().detect(file_path, object_type)
-    @staticmethod
-    def point(file_path, object_type):
-        return _get_client().point(file_path, object_type)
-
-class ASR:
-    @staticmethod
-    def transcribe(file_path, language):
-        return _get_client().transcribe(file_path, language)
-    @staticmethod
-    def transcribe_batch(file_paths, language):
-        return _get_client().transcribe_batch(file_paths, language)

client.py

@@ -1,127 +0,0 @@
-import os
-import requests
-from .exceptions import DhwaniAPIError
-
-class DhwaniClient:
-    def __init__(self, api_key=None, api_base=None):
-        self.api_key = api_key or os.getenv("DHWANI_API_KEY")
-        self.api_base = api_base or os.getenv("DHWANI_API_BASE", "http://localhost:7860")
-        if not self.api_key:
-            raise ValueError("DHWANI_API_KEY not set")
-
-    def _headers(self):
-        return {"X-API-Key": self.api_key}
-
-    def chat(self, prompt):
-        resp = requests.post(
-            f"{self.api_base}/chat",
-            headers={**self._headers(), "Content-Type": "application/json"},
-            json={"prompt": prompt}
-        )
-        if resp.status_code != 200:
-            raise DhwaniAPIError(resp)
-        return resp.json()
-
-    def speech(self, input, voice, model, response_format="mp3", output_file=None):
-        data = {
-            "input": input,
-            "voice": voice,
-            "model": model,
-            "response_format": response_format
-        }
-        resp = requests.post(
-            f"{self.api_base}/v1/audio/speech",
-            headers={**self._headers(), "Content-Type": "application/json"},
-            json=data,
-            stream=True
-        )
-        if resp.status_code != 200:
-            raise DhwaniAPIError(resp)
-        if output_file:
-            with open(output_file, "wb") as f:
-                for chunk in resp.iter_content(chunk_size=8192):
-                    f.write(chunk)
-            return output_file
-        return resp.content
-
-    def caption(self, file_path, length="short"):
-        with open(file_path, "rb") as f:
-            files = {"file": f}
-            data = {"length": length}
-            resp = requests.post(
-                f"{self.api_base}/caption/",
-                headers=self._headers(),
-                files=files,
-                data=data
-            )
-        if resp.status_code != 200:
-            raise DhwaniAPIError(resp)
-        return resp.json()
-
-    def visual_query(self, file_path, query):
-        with open(file_path, "rb") as f:
-            files = {"file": f}
-            data = {"query": query}
-            resp = requests.post(
-                f"{self.api_base}/visual_query/",
-                headers=self._headers(),
-                files=files,
-                data=data
-            )
-        if resp.status_code != 200:
-            raise DhwaniAPIError(resp)
-        return resp.json()
-
-    def detect(self, file_path, object_type):
-        with open(file_path, "rb") as f:
-            files = {"file": f}
-            data = {"object_type": object_type}
-            resp = requests.post(
-                f"{self.api_base}/detect/",
-                headers=self._headers(),
-                files=files,
-                data=data
-            )
-        if resp.status_code != 200:
-            raise DhwaniAPIError(resp)
-        return resp.json()
-
-    def point(self, file_path, object_type):
-        with open(file_path, "rb") as f:
-            files = {"file": f}
-            data = {"object_type": object_type}
-            resp = requests.post(
-                f"{self.api_base}/point/",
-                headers=self._headers(),
-                files=files,
-                data=data
-            )
-        if resp.status_code != 200:
-            raise DhwaniAPIError(resp)
-        return resp.json()
-
-    def transcribe(self, file_path, language):
-        with open(file_path, "rb") as f:
-            files = {"file": f}
-            resp = requests.post(
-                f"{self.api_base}/transcribe/?language={language}",
-                headers=self._headers(),
-                files=files
-            )
-        if resp.status_code != 200:
-            raise DhwaniAPIError(resp)
-        return resp.json()
-
-    def transcribe_batch(self, file_paths, language):
-        files = [("files", open(fp, "rb")) for fp in file_paths]
-        resp = requests.post(
-            f"{self.api_base}/transcribe_batch/?language={language}",
-            headers=self._headers(),
-            files=files
-        )
-        # Close all files
-        for _, f in files:
-            f.close()
-        if resp.status_code != 200:
-            raise DhwaniAPIError(resp)
-        return resp.json()

dwani-0.1.0.dist-info/METADATA

@@ -1,181 +0,0 @@
-Metadata-Version: 2.4
-Name: dwani
-Version: 0.1.0
-Summary: Multimodal AI server for Indian languages (speech, vision, LLMs, TTS, ASR, etc.)
-Author-email: sachin <python@dwani.ai>
-Project-URL: Homepage, https://github.com/dwani-ai/dwani-server
-Project-URL: Source, https://github.com/dwani-ai/dwani-server
-Project-URL: Issues, https://github.com/dwani-ai/dwani-server/issues
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-Requires-Dist: torch==2.6.0
-Requires-Dist: torchvision
-Requires-Dist: torchaudio==2.6.0
-Requires-Dist: accelerate==1.6.0
-Requires-Dist: bitsandbytes==0.45.5
-Requires-Dist: pillow==11.1.0
-Requires-Dist: uvicorn==0.34.0
-Requires-Dist: fastapi==0.115.12
-Requires-Dist: pydantic-settings
-Requires-Dist: slowapi
-Requires-Dist: python-multipart==0.0.20
-Requires-Dist: packaging==24.2
-Requires-Dist: tenacity
-Requires-Dist: num2words
-Requires-Dist: sentencepiece
-Requires-Dist: huggingface-hub==0.27.1
-Requires-Dist: openai
-Requires-Dist: flash-attn
-Requires-Dist: onnx==1.16.2
-Requires-Dist: onnxruntime==1.21.0
-Requires-Dist: onnxruntime-gpu==1.21.0
-Requires-Dist: pydub==0.25.1
-Requires-Dist: hf_xet
-Requires-Dist: aiofiles==23.2.1
-Requires-Dist: aiohappyeyeballs==2.6.1
-Requires-Dist: aiohttp==3.11.16
-Requires-Dist: aiosignal==1.3.2
-Requires-Dist: annotated-types==0.7.0
-Requires-Dist: antlr4-python3-runtime==4.9.3
-Requires-Dist: anyio==4.9.0
-Requires-Dist: async-timeout==5.0.1
-Requires-Dist: attrs==25.3.0
-Requires-Dist: audioread==3.0.1
-Requires-Dist: boto3==1.37.29
-Requires-Dist: botocore==1.37.29
-Requires-Dist: cached_path==1.7.1
-Requires-Dist: cachetools==5.5.2
-Requires-Dist: certifi==2025.1.31
-Requires-Dist: cffi==1.17.1
-Requires-Dist: charset-normalizer==3.4.1
-Requires-Dist: click==8.1.8
-Requires-Dist: contourpy==1.3.1
-Requires-Dist: cycler==0.12.1
-Requires-Dist: datasets==3.5.0
-Requires-Dist: decorator==5.2.1
-Requires-Dist: dill==0.3.8
-Requires-Dist: docker-pycreds==0.4.0
-Requires-Dist: einops==0.8.1
-Requires-Dist: einx==0.3.0
-Requires-Dist: ema-pytorch==0.7.7
-Requires-Dist: encodec==0.1.1
-Requires-Dist: exceptiongroup==1.2.2
-Requires-Dist: f5-tts==1.1.0
-Requires-Dist: ffmpy==0.5.0
-Requires-Dist: filelock==3.18.0
-Requires-Dist: fonttools==4.57.0
-Requires-Dist: frozendict==2.4.6
-Requires-Dist: frozenlist==1.5.0
-Requires-Dist: fsspec==2024.12.0
-Requires-Dist: gitdb==4.0.12
-Requires-Dist: GitPython==3.1.44
-Requires-Dist: google-api-core==2.24.2
-Requires-Dist: google-auth==2.38.0
-Requires-Dist: google-cloud-core==2.4.3
-Requires-Dist: google-cloud-storage==2.19.0
-Requires-Dist: google-crc32c==1.7.1
-Requires-Dist: google-resumable-media==2.7.2
-Requires-Dist: googleapis-common-protos==1.69.2
-Requires-Dist: gradio==5.14.0
-Requires-Dist: gradio_client==1.7.0
-Requires-Dist: groovy==0.1.2
-Requires-Dist: h11==0.14.0
-Requires-Dist: httpcore==1.0.7
-Requires-Dist: httpx==0.28.1
-Requires-Dist: hydra-core==1.3.2
-Requires-Dist: idna==3.10
-Requires-Dist: jieba==0.42.1
-Requires-Dist: Jinja2==3.1.6
-Requires-Dist: jmespath==1.0.1
-Requires-Dist: joblib==1.4.2
-Requires-Dist: kiwisolver==1.4.8
-Requires-Dist: lazy_loader==0.4
-Requires-Dist: librosa==0.11.0
-Requires-Dist: llvmlite==0.44.0
-Requires-Dist: loguru==0.7.3
-Requires-Dist: markdown-it-py==3.0.0
-Requires-Dist: MarkupSafe==2.1.5
-Requires-Dist: matplotlib==3.10.1
-Requires-Dist: mdurl==0.1.2
-Requires-Dist: mpmath==1.3.0
-Requires-Dist: msgpack==1.1.0
-Requires-Dist: multidict==6.3.2
-Requires-Dist: multiprocess==0.70.16
-Requires-Dist: networkx==3.4.2
-Requires-Dist: numba==0.61.0
-Requires-Dist: numpy==1.26.4
-Requires-Dist: nvidia-cublas-cu12==12.4.5.8
-Requires-Dist: nvidia-cuda-cupti-cu12==12.4.127
-Requires-Dist: nvidia-cuda-nvrtc-cu12==12.4.127
-Requires-Dist: nvidia-cuda-runtime-cu12==12.4.127
-Requires-Dist: nvidia-cudnn-cu12==9.1.0.70
-Requires-Dist: nvidia-cufft-cu12==11.2.1.3
-Requires-Dist: nvidia-curand-cu12==10.3.5.147
-Requires-Dist: nvidia-cusolver-cu12==11.6.1.9
-Requires-Dist: nvidia-cusparse-cu12==12.3.1.170
-Requires-Dist: nvidia-cusparselt-cu12==0.6.2
-Requires-Dist: nvidia-nccl-cu12==2.21.5
-Requires-Dist: nvidia-nvjitlink-cu12==12.4.127
-Requires-Dist: nvidia-nvtx-cu12==12.4.127
-Requires-Dist: omegaconf==2.3.0
-Requires-Dist: orjson==3.10.16
-Requires-Dist: pandas==2.2.3
-Requires-Dist: platformdirs==4.3.7
-Requires-Dist: pooch==1.8.2
-Requires-Dist: propcache==0.3.1
-Requires-Dist: proto-plus==1.26.1
-Requires-Dist: protobuf
-Requires-Dist: psutil==7.0.0
-Requires-Dist: pyarrow==19.0.1
-Requires-Dist: pyasn1==0.6.1
-Requires-Dist: pyasn1_modules==0.4.2
-Requires-Dist: pycparser==2.22
-Requires-Dist: pydantic==2.10.6
-Requires-Dist: pydantic_core==2.27.2
-Requires-Dist: Pygments==2.19.1
-Requires-Dist: pyparsing==3.2.3
-Requires-Dist: pypinyin==0.54.0
-Requires-Dist: python-dateutil==2.9.0.post0
-Requires-Dist: pytz==2025.2
-Requires-Dist: PyYAML==6.0.2
-Requires-Dist: regex==2024.11.6
-Requires-Dist: requests==2.32.3
-Requires-Dist: rich==13.9.4
-Requires-Dist: rsa==4.9
-Requires-Dist: ruff==0.11.4
-Requires-Dist: s3transfer==0.11.4
-Requires-Dist: safehttpx==0.1.6
-Requires-Dist: safetensors==0.5.3
-Requires-Dist: scikit-learn==1.6.1
-Requires-Dist: scipy==1.15.2
-Requires-Dist: semantic-version==2.10.0
-Requires-Dist: sentry-sdk==2.25.1
-Requires-Dist: setproctitle==1.3.5
-Requires-Dist: shellingham==1.5.4
-Requires-Dist: six==1.17.0
-Requires-Dist: smmap==5.0.2
-Requires-Dist: sniffio==1.3.1
-Requires-Dist: soundfile==0.13.1
-Requires-Dist: soxr==0.5.0.post1
-Requires-Dist: starlette==0.46.1
-Requires-Dist: sympy==1.13.1
-Requires-Dist: threadpoolctl==3.6.0
-Requires-Dist: tokenizers==0.21.1
-Requires-Dist: tomli==2.2.1
-Requires-Dist: tomlkit==0.13.2
-Requires-Dist: torchdiffeq==0.2.5
-Requires-Dist: tqdm==4.67.1
-Requires-Dist: transformers==4.50.3
-Requires-Dist: transformers-stream-generator==0.0.5
-Requires-Dist: triton==3.2.0
-Requires-Dist: typer==0.15.2
-Requires-Dist: typing-inspection==0.4.0
-Requires-Dist: typing_extensions==4.13.1
-Requires-Dist: tzdata==2025.2
-Requires-Dist: urllib3==2.3.0
-Requires-Dist: vocos==0.1.0
-Requires-Dist: wandb==0.19.9
-Requires-Dist: websockets==14.2
-Requires-Dist: x-transformers==2.2.8
-Requires-Dist: xxhash==3.5.0
-Requires-Dist: yarl==1.19.0

dwani-0.1.0.dist-info/RECORD

@@ -1,12 +0,0 @@
-__init__.py,sha256=2tm2TJE5xuE6thkMj7um0xxCCmLE4OHtUM-M3M0H8Yo,1294
-asr.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-audio.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chat.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-client.py,sha256=BLWnHoehLZhXuDd8IPitLyuo3STmhn3TQWBziz5TXZ4,4219
-docs.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-exceptions.py,sha256=qEN5ukqlnN7v-kHNEnISWFMpPMt6uTft9mPsTXJ4LVA,227
-vision.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-dwani-0.1.0.dist-info/METADATA,sha256=XQXwaL4Yk7_ufDAZwfg1AZDWbRt4ZpcXnnDiqEeQCRE,6100
-dwani-0.1.0.dist-info/WHEEL,sha256=0CuiUZ_p9E4cD6NyLD6UG80LBXYyiSYZOKDm5lp32xk,91
-dwani-0.1.0.dist-info/top_level.txt,sha256=7MBQ5IZg4CXEAt-rxOplIWS0HQcybyibcos1F-zrfOY,54
-dwani-0.1.0.dist-info/RECORD,,

dwani-0.1.0.dist-info/top_level.txt

@@ -1,8 +0,0 @@
-__init__
-asr
-audio
-chat
-client
-docs
-exceptions
-vision