Metadata-Version: 2.4
Name: sonorus-ai
Version: 0.1.0
Summary: Sonorus AI: Robust Speech Recognition and Hinglish Transcription
Author: Krishnanshu
License-Expression: MIT
Project-URL: Homepage, https://github.com/Krishnanshu/sonorus-ai
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: more-itertools
Requires-Dist: numba
Requires-Dist: numpy
Requires-Dist: tiktoken
Requires-Dist: torch
Requires-Dist: tqdm
Requires-Dist: triton>=2; (platform_machine == "x86_64" and sys_platform == "linux") or sys_platform == "linux2"
Provides-Extra: dev
Requires-Dist: black; extra == "dev"
Requires-Dist: flake8; extra == "dev"
Requires-Dist: isort; extra == "dev"
Requires-Dist: pytest; extra == "dev"
Requires-Dist: scipy; extra == "dev"
Dynamic: license-file

# Sonorus AI (sonorus-ai)

**Sonorus AI** is an enhanced, robust speech recognition library built on top of OpenAI's Whisper, featuring:
- **Native Hinglish Transcription:** Transcribes Hindi speech directly into clean, phonetic Roman English letters (`--language Hinglish`).
- **Phonetic Corrections:** Built-in vocabulary post-processing to correct common speech transliteration slips (e.g. `bina bikhar`, `mohabbat`, `guroor`).
- **Clean Output Organization:** Automatically organizes transcriptions into language folders (e.g. `outputs/Hindi/`, `outputs/Hinglish/`, `outputs/English/`) in `.txt` format without cluttering the project root.

## Setup

You can install Sonorus AI directly using `pip`:

```bash
pip install sonorus-ai
```

Or install in editable mode for local development:

```bash
pip install -e .
```

To update the package to the latest version of this repository, please run:

```bash
pip install --upgrade --no-deps --force-reinstall git+https://github.com/Krishnanshu/sonorus-ai.git
```

It also requires the command-line tool [`ffmpeg`](https://ffmpeg.org/) to be installed on your system, which is available from most package managers:

```bash
# on Ubuntu or Debian
sudo apt update && sudo apt install ffmpeg

# on Arch Linux
sudo pacman -S ffmpeg

# on MacOS using Homebrew (https://brew.sh/)
brew install ffmpeg

# on Windows using Chocolatey (https://chocolatey.org/)
choco install ffmpeg

# on Windows using Scoop (https://scoop.sh/)
scoop install ffmpeg
```

You may need [`rust`](http://rust-lang.org) installed as well, in case [tiktoken](https://github.com/openai/tiktoken) does not provide a pre-built wheel for your platform. If you see installation errors during the `pip install` command above, please follow the [Getting started page](https://www.rust-lang.org/learn/get-started) to install Rust development environment. Additionally, you may need to configure the `PATH` environment variable, e.g. `export PATH="$HOME/.cargo/bin:$PATH"`. If the installation fails with `No module named 'setuptools_rust'`, you need to install `setuptools_rust`, e.g. by running:

```bash
pip install setuptools-rust
```

## Available models and languages

There are six model sizes, four with English-only versions, offering speed and accuracy tradeoffs.
Below are the names of the available models and their approximate memory requirements and inference speed relative to the large model.
The relative speeds below are measured by transcribing English speech on a A100, and the real-world speed may vary significantly depending on many factors including the language, the speaking speed, and the available hardware.

|  Size  | Parameters | English-only model | Multilingual model | Required VRAM | Relative speed |
| :----: | :--------: | :----------------: | :----------------: | :-----------: | :------------: |
|  tiny  |    39 M    |     `tiny.en`      |       `tiny`       |     ~1 GB     |      ~10x      |
|  base  |    74 M    |     `base.en`      |       `base`       |     ~1 GB     |      ~7x       |
| small  |   244 M    |     `small.en`     |      `small`       |     ~2 GB     |      ~4x       |
| medium |   769 M    |    `medium.en`     |      `medium`      |     ~5 GB     |      ~2x       |
| large  |   1550 M   |        N/A         |      `large`       |    ~10 GB     |       1x       |
| turbo  |   809 M    |        N/A         |      `turbo`       |     ~6 GB     |      ~8x       |

The `.en` models for English-only applications tend to perform better, especially for the `tiny.en` and `base.en` models. We observed that the difference becomes less significant for the `small.en` and `medium.en` models.
Additionally, the `turbo` model is an optimized version of `large-v3` that offers faster transcription speed with a minimal degradation in accuracy.

Model performance varies depending on the language. The figure below shows a performance breakdown of `large-v3` and `large-v2` models by language, evaluated on the Common Voice 15 and Fleurs datasets.

![WER breakdown by language](https://github.com/openai/whisper/assets/266841/f4619d66-1058-4005-8f67-a9d811b77c62)

## Command-line usage

Transcribe speech in audio/video files directly from your terminal using `sonorus` (or `sonorus-ai`):

```bash
# Transcribe Hinglish with automated phonetic correction & clean folder organization
sonorus "audio.mp4" --model turbo --language Hinglish

# Transcribe multiple files
sonorus audio.flac audio.mp3 audio.wav --model turbo
```

The default setting (which selects the `turbo` model) works well for transcribing English and Hinglish. However, **the `turbo` model is not trained for translation tasks**. If you need to **translate non-English speech into English**, use one of the **multilingual models** (`tiny`, `base`, `small`, `medium`, `large`) instead of `turbo`.

For example, to transcribe an audio file containing non-English speech, you can specify the language:

```bash
sonorus japanese.wav --language Japanese
```

To **translate** speech into English, use:

```bash
sonorus japanese.wav --model medium --language Japanese --task translate
```

> **Note:** The `turbo` model will return the original language even if `--task translate` is specified. Use `medium` or `large` for the best translation results.

Run the following to view all available options:

```bash
sonorus --help
```

## Python usage

Transcription can also be performed within Python:

```python
import sonorus

model = sonorus.load_model("turbo")
result = model.transcribe("audio.mp3")
print(result["text"])
```

Internally, the `transcribe()` method reads the entire file and processes the audio with a sliding 30-second window, performing autoregressive sequence-to-sequence predictions on each window.

Below is an example usage of `sonorus.detect_language()` and `sonorus.decode()` which provide lower-level access to the model:

```python
import sonorus

model = sonorus.load_model("turbo")

# load audio and pad/trim it to fit 30 seconds
audio = sonorus.load_audio("audio.mp3")
audio = sonorus.pad_or_trim(audio)

# make log-Mel spectrogram and move to the same device as the model
mel = sonorus.log_mel_spectrogram(audio, n_mels=model.dims.n_mels).to(model.device)

# detect the spoken language
_, probs = model.detect_language(mel)
print(f"Detected language: {max(probs, key=probs.get)}")

# decode the audio
options = sonorus.DecodingOptions()
result = sonorus.decode(model, mel, options)

# print the recognized text
print(result.text)
```

## More examples

Please use the [🙌 Show and tell](https://github.com/openai/whisper/discussions/categories/show-and-tell) category in Discussions for sharing more example usages of Whisper and third-party extensions such as web demos, integrations with other tools, ports for different platforms, etc.

## License

Whisper's code and model weights are released under the MIT License. See [LICENSE](https://github.com/openai/whisper/blob/main/LICENSE) for further details.
