<div align="center">
<h1>Common ML Functionalities API</h1>
<img src="./cover-image.png" height="200" width="200">
<h4>
Python package which provides useful and common interactions with ML functionalities <br /> such as detecting language, chatbots,
link transcriptions, audio enhancements, and much more.
</h4>
<h5>Powered by <a href="https://www.sievedata.com/">Sieve</a>, <a href="https://www.langchain.com/">Langchain</a></h5>
</div>
<br />
<br />
## Features
- **Translation (sieve/seamless_text2text)**: Translates text from a source language to a target language.
- **Youtube Link Transcription (langchain/youtube_transcripts)**: Transcribes audio from a given URL.
- **Detect Language (sieve)**: Identifies the language of the given text.
- **Text to Speech (sieve)**: Converts text into spoken words.
- **Translate and Talk (sieve)**: Translates text from one language to another and then converts the translated text to speech.
- **Youtube Video Download (sieve)**: Downloads a Youtube video in MP4 format given its URL.
- **Detect Language and Translate**: Detects the language of the text and translates it to a specified target language.
- **Audio Enhancement (sieve)**: Enhances the quality of an mp3 or wav file.
- **Visual question answering (sieve/llava-vl-13b)**: Visual question answering with GPT-4 level capabilities.
<br />
## Setup
To set up the package, follow these steps:
1. **Install the Package**: Install this package using pip:
pip install common-ml-functions
2. **Import in Your Project**: Import the required functionalities in your Python project:
```python
from common-ml-functions.translation import translate
from common-ml-functions.text_to_speech import convert_text_to_speech
# ... other imports as needed
```
<br />
## Usage
The package offers a range of functionalities that can be easily integrated into Python projects. Here are some of the features and how to use them:
<br />
**Translation**: Use `translate(original_text, source_language, target_language)` to translate text. <br />
```python
from common-ml-functions.language import translate
translated_text = translate("Hello, world!", "en", "es")
print(translated_text)
```
<br />
**Youtube Link Transcription**: Use `yb_transcript(url)` to get transcriptions of YouTube videos. <br />
```python
from common-ml-functions.yb import yb_transcript
transcript = yb_transcript("https://www.youtube.com/watch?v=example")
print("Transcript:", transcript)
```
<br />
**Detect Language**: Use `detect(text)` to identify the language of a given text. <br />
```python
from common-ml-functions.language import detect
language_code = detect("Ceci est un texte en français.")
print(f"The detected language code is: {language_code}")
```
<br />
**Text to Speech**: Use `convert_text_to_speech(text)` to convert text into speech. <br />
```python
from common-ml-functions.text_to_speech import convert_text_to_speech
audio_file_path = convert_text_to_speech("Hello, this is a test.")
print(f"Audio file saved at: {audio_file_path}")
```
<br />
**Translate and Talk**: Use `translate_and_talk(text, target_language)` to translate and convert text to speech. <br />
```python
from common-ml-functions.text_to_speech import translate_and_talk
audio_file_path = translate_and_talk("This is a test.", "es")
print(f"Translated and converted to speech, file saved at: {audio_file_path}")
```
<br />
**Youtube Video Download**: Use `yb_download(url)` to download YouTube videos. <br />
```python
from common-ml-functions.yb import yb_download
video_path = yb_download("https://www.youtube.com/watch?v=example")
print(f"Video downloaded at: {video_path}")
```
<br />
**Detect Language and Translate**: Combine detect and translate for detecting and translating text. <br />
```python
from common-ml-functions.language import detect_and_translate
translated_text = detect_and_translate("Bonjour le monde!", "en")
print(translated_text)
```
<br />
**Audio Enhancement**: Use `enhance_audio(audio_url, speed_boost, steps)` for audio enhancement. <br />
```python
from common-ml-functions.audio import enhance_audio
enhanced_audio_path = enhance_audio("http://example.com/audio.mp3", True, 50)
print(f"Enhanced audio saved at: {enhanced_audio_path}")
```
<br />
**Visual question answering**: Use `visual_question_answering(image_url, prompt)` for visual Q&A. <br />
```python
from common-ml-functions.visual import visual_question_answering
answer = visual_question_answering("http://example.com/image.jpg", "What is depicted in this image?")
print(answer)
```
<br />
## Contributing!
Please consider contributing to this young and humble project!
Email any questions at andere.emi@gmail.com
Raw data
{
"_id": null,
"home_page": "https://github.com/technoabsurdist/ml-api",
"name": "common-ml-functions",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": "",
"keywords": "common-ml-functions,language processing,youtube downloader,text-to-speech",
"author": "Techno Absurdist",
"author_email": "andere.emi@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/df/07/27a05ab047cf2ced4ba49073a1a38d62612b24407a7e57e05d68718c8c52/common-ml-functions-0.1.1.tar.gz",
"platform": null,
"description": "\n<div align=\"center\"> \n <h1>Common ML Functionalities API</h1>\n <img src=\"./cover-image.png\" height=\"200\" width=\"200\">\n <h4>\n Python package which provides useful and common interactions with ML functionalities <br /> such as detecting language, chatbots, \n link transcriptions, audio enhancements, and much more. \n </h4>\n <h5>Powered by <a href=\"https://www.sievedata.com/\">Sieve</a>, <a href=\"https://www.langchain.com/\">Langchain</a></h5>\n\n</div>\n\n<br />\n<br />\n\n## Features\n\n- **Translation (sieve/seamless_text2text)**: Translates text from a source language to a target language.\n- **Youtube Link Transcription (langchain/youtube_transcripts)**: Transcribes audio from a given URL.\n- **Detect Language (sieve)**: Identifies the language of the given text.\n- **Text to Speech (sieve)**: Converts text into spoken words.\n- **Translate and Talk (sieve)**: Translates text from one language to another and then converts the translated text to speech.\n- **Youtube Video Download (sieve)**: Downloads a Youtube video in MP4 format given its URL.\n- **Detect Language and Translate**: Detects the language of the text and translates it to a specified target language.\n- **Audio Enhancement (sieve)**: Enhances the quality of an mp3 or wav file. \n- **Visual question answering (sieve/llava-vl-13b)**: Visual question answering with GPT-4 level capabilities.\n\n\n<br />\n\n## Setup\n\nTo set up the package, follow these steps:\n\n1. **Install the Package**: Install this package using pip:\npip install common-ml-functions\n\n2. **Import in Your Project**: Import the required functionalities in your Python project:\n```python\nfrom common-ml-functions.translation import translate\nfrom common-ml-functions.text_to_speech import convert_text_to_speech\n# ... other imports as needed\n```\n\n<br />\n\n## Usage\n\nThe package offers a range of functionalities that can be easily integrated into Python projects. Here are some of the features and how to use them:\n\n<br />\n\n**Translation**: Use `translate(original_text, source_language, target_language)` to translate text. <br />\n```python\nfrom common-ml-functions.language import translate\n\ntranslated_text = translate(\"Hello, world!\", \"en\", \"es\")\nprint(translated_text)\n```\n<br />\n\n**Youtube Link Transcription**: Use `yb_transcript(url)` to get transcriptions of YouTube videos. <br />\n```python\nfrom common-ml-functions.yb import yb_transcript\n\ntranscript = yb_transcript(\"https://www.youtube.com/watch?v=example\")\nprint(\"Transcript:\", transcript)\n```\n<br />\n\n**Detect Language**: Use `detect(text)` to identify the language of a given text. <br />\n```python\nfrom common-ml-functions.language import detect\n\nlanguage_code = detect(\"Ceci est un texte en fran\u00e7ais.\")\nprint(f\"The detected language code is: {language_code}\")\n```\n<br />\n\n**Text to Speech**: Use `convert_text_to_speech(text)` to convert text into speech. <br />\n```python\nfrom common-ml-functions.text_to_speech import convert_text_to_speech\n\naudio_file_path = convert_text_to_speech(\"Hello, this is a test.\")\nprint(f\"Audio file saved at: {audio_file_path}\")\n```\n<br />\n\n**Translate and Talk**: Use `translate_and_talk(text, target_language)` to translate and convert text to speech. <br />\n```python\nfrom common-ml-functions.text_to_speech import translate_and_talk\n\naudio_file_path = translate_and_talk(\"This is a test.\", \"es\")\nprint(f\"Translated and converted to speech, file saved at: {audio_file_path}\")\n```\n<br />\n\n**Youtube Video Download**: Use `yb_download(url)` to download YouTube videos. <br />\n```python\nfrom common-ml-functions.yb import yb_download\n\nvideo_path = yb_download(\"https://www.youtube.com/watch?v=example\")\nprint(f\"Video downloaded at: {video_path}\")\n```\n<br />\n\n**Detect Language and Translate**: Combine detect and translate for detecting and translating text. <br />\n```python\nfrom common-ml-functions.language import detect_and_translate\n\ntranslated_text = detect_and_translate(\"Bonjour le monde!\", \"en\")\nprint(translated_text)\n```\n<br />\n\n**Audio Enhancement**: Use `enhance_audio(audio_url, speed_boost, steps)` for audio enhancement. <br />\n```python\nfrom common-ml-functions.audio import enhance_audio\n\nenhanced_audio_path = enhance_audio(\"http://example.com/audio.mp3\", True, 50)\nprint(f\"Enhanced audio saved at: {enhanced_audio_path}\")\n```\n<br />\n\n**Visual question answering**: Use `visual_question_answering(image_url, prompt)` for visual Q&A. <br /> \n```python\nfrom common-ml-functions.visual import visual_question_answering\n\nanswer = visual_question_answering(\"http://example.com/image.jpg\", \"What is depicted in this image?\")\nprint(answer)\n```\n<br />\n\n\n## Contributing!\nPlease consider contributing to this young and humble project! \nEmail any questions at andere.emi@gmail.com\n",
"bugtrack_url": null,
"license": "",
"summary": "A python package for out-of-the-box ML solutions",
"version": "0.1.1",
"project_urls": {
"Homepage": "https://github.com/technoabsurdist/ml-api"
},
"split_keywords": [
"common-ml-functions",
"language processing",
"youtube downloader",
"text-to-speech"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "bbd7e32a3451f2c00a9b859828eb413117fb85489f5f632d416c42c71b7f86d9",
"md5": "2430c6d3d6a425705d4dec9cd9b746f4",
"sha256": "d3573ce859a4b80eaa535b2651ee9962ec9ae63047448d0e83b77b9736c94a5d"
},
"downloads": -1,
"filename": "common_ml_functions-0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "2430c6d3d6a425705d4dec9cd9b746f4",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 2974,
"upload_time": "2023-11-29T02:24:20",
"upload_time_iso_8601": "2023-11-29T02:24:20.444605Z",
"url": "https://files.pythonhosted.org/packages/bb/d7/e32a3451f2c00a9b859828eb413117fb85489f5f632d416c42c71b7f86d9/common_ml_functions-0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "df0727a05ab047cf2ced4ba49073a1a38d62612b24407a7e57e05d68718c8c52",
"md5": "b60a87771021c31fb10e27c004db27f0",
"sha256": "96d097218d7863d4a7f5f222d68065bf380d9d235ba8fd9ceab9c2cc80001891"
},
"downloads": -1,
"filename": "common-ml-functions-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "b60a87771021c31fb10e27c004db27f0",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 3363,
"upload_time": "2023-11-29T02:24:22",
"upload_time_iso_8601": "2023-11-29T02:24:22.248588Z",
"url": "https://files.pythonhosted.org/packages/df/07/27a05ab047cf2ced4ba49073a1a38d62612b24407a7e57e05d68718c8c52/common-ml-functions-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-11-29 02:24:22",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "technoabsurdist",
"github_project": "ml-api",
"github_not_found": true,
"lcname": "common-ml-functions"
}
JSON
