sonorus-ai 0.1.0__tar.gz

sonorus_ai-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2022 OpenAI
+
+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.

sonorus_ai-0.1.0/MANIFEST.in

@@ -0,0 +1,5 @@
+include requirements.txt
+include README.md
+include LICENSE
+include sonorus/assets/*
+include sonorus/normalizers/english.json

sonorus_ai-0.1.0/PKG-INFO

@@ -0,0 +1,187 @@
+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.

sonorus_ai-0.1.0/README.md

@@ -0,0 +1,155 @@
+# 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.

sonorus_ai-0.1.0/pyproject.toml

@@ -0,0 +1,54 @@
+[build-system]
+build-backend = "setuptools.build_meta"
+
+requires = [ "setuptools>=61.2" ]
+
+[project]
+name = "sonorus-ai"
+description = "Sonorus AI: Robust Speech Recognition and Hinglish Transcription"
+readme.content-type = "text/markdown"
+readme.file = "README.md"
+license = "MIT"
+authors = [ { name = "Krishnanshu" } ]
+requires-python = ">=3.8"
+classifiers = [
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.8",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+]
+dynamic = [ "version" ]
+dependencies = [
+  "more-itertools",
+  "numba",
+  "numpy",
+  "tiktoken",
+  "torch",
+  "tqdm",
+  "triton>=2; (platform_machine=='x86_64' and sys_platform=='linux') or sys_platform=='linux2'",
+]
+optional-dependencies.dev = [ "black", "flake8", "isort", "pytest", "scipy" ]
+urls = { Homepage = "https://github.com/Krishnanshu/sonorus-ai" }
+scripts.sonorus = "sonorus.transcribe:cli"
+scripts.sonorus-ai = "sonorus.transcribe:cli"
+
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.dynamic]
+version = { attr = "sonorus.version.__version__" }
+
+[tool.setuptools.packages.find]
+exclude = [ "tests*" ]
+namespaces = false
+
+[tool.black]
+
+[tool.isort]
+profile = "black"
+include_trailing_comma = true
+line_length = 88
+multi_line_output = 3

sonorus_ai-0.1.0/requirements.txt

@@ -0,0 +1,7 @@
+numba
+numpy
+torch
+tqdm
+more-itertools
+tiktoken
+triton>=2.0.0;platform_machine=="x86_64" and sys_platform=="linux" or sys_platform=="linux2"

sonorus_ai-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

sonorus_ai-0.1.0/sonorus/__init__.py

@@ -0,0 +1,166 @@
+import hashlib
+import io
+import os
+import urllib
+import warnings
+from typing import List, Optional, Union
+
+import torch
+from tqdm import tqdm
+
+from .audio import load_audio, log_mel_spectrogram, pad_or_trim
+from .decoding import DecodingOptions, DecodingResult, decode, detect_language
+from .model import ModelDimensions, Whisper
+from .transcribe import transcribe
+from .version import __version__
+
+_MODELS = {
+    "tiny.en": "https://openaipublic.azureedge.net/main/whisper/models/d3dd57d32accea0b295c96e26691aa14d8822fac7d9d27d5dc00b4ca2826dd03/tiny.en.pt",
+    "tiny": "https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt",
+    "base.en": "https://openaipublic.azureedge.net/main/whisper/models/25a8566e1d0c1e2231d1c762132cd20e0f96a85d16145c3a00adf5d1ac670ead/base.en.pt",
+    "base": "https://openaipublic.azureedge.net/main/whisper/models/ed3a0b6b1c0edf879ad9b11b1af5a0e6ab5db9205f891f668f8b0e6c6326e34e/base.pt",
+    "small.en": "https://openaipublic.azureedge.net/main/whisper/models/f953ad0fd29cacd07d5a9eda5624af0f6bcf2258be67c92b79389873d91e0872/small.en.pt",
+    "small": "https://openaipublic.azureedge.net/main/whisper/models/9ecf779972d90ba49c06d968637d720dd632c55bbf19d441fb42bf17a411e794/small.pt",
+    "medium.en": "https://openaipublic.azureedge.net/main/whisper/models/d7440d1dc186f76616474e0ff0b3b6b879abc9d1a4926b7adfa41db2d497ab4f/medium.en.pt",
+    "medium": "https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt",
+    "large-v1": "https://openaipublic.azureedge.net/main/whisper/models/e4b87e7e0bf463eb8e6956e646f1e277e901512310def2c24bf0e11bd3c28e9a/large-v1.pt",
+    "large-v2": "https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt",
+    "large-v3": "https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt",
+    "large": "https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt",
+    "large-v3-turbo": "https://openaipublic.azureedge.net/main/whisper/models/aff26ae408abcba5fbf8813c21e62b0941638c5f6eebfb145be0c9839262a19a/large-v3-turbo.pt",
+    "turbo": "https://openaipublic.azureedge.net/main/whisper/models/aff26ae408abcba5fbf8813c21e62b0941638c5f6eebfb145be0c9839262a19a/large-v3-turbo.pt",
+}
+
+# base85-encoded (n_layers, n_heads) boolean arrays indicating the cross-attention heads that are
+# highly correlated to the word-level timing, i.e. the alignment between audio and text tokens.
+_ALIGNMENT_HEADS = {
+    "tiny.en": b"ABzY8J1N>@0{>%R00Bk>$p{7v037`oCl~+#00",
+    "tiny": b"ABzY8bu8Lr0{>%RKn9Fp%m@SkK7Kt=7ytkO",
+    "base.en": b"ABzY8;40c<0{>%RzzG;p*o+Vo09|#PsxSZm00",
+    "base": b"ABzY8KQ!870{>%RzyTQH3`Q^yNP!>##QT-<FaQ7m",
+    "small.en": b"ABzY8>?_)10{>%RpeA61k&I|OI3I$65C{;;pbCHh0B{qLQ;+}v00",
+    "small": b"ABzY8DmU6=0{>%Rpa?J`kvJ6qF(V^F86#Xh7JUGMK}P<N0000",
+    "medium.en": b"ABzY8usPae0{>%R7<zz_OvQ{)4kMa0BMw6u5rT}kRKX;$NfYBv00*Hl@qhsU00",
+    "medium": b"ABzY8B0Jh+0{>%R7}kK1fFL7w6%<-Pf*t^=N)Qr&0RR9",
+    "large-v1": b"ABzY8r9j$a0{>%R7#4sLmoOs{s)o3~84-RPdcFk!JR<kSfC2yj",
+    "large-v2": b"ABzY8zd+h!0{>%R7=D0pU<_bnWW*tkYAhobTNnu$jnkEkXqp)j;w1Tzk)UH3X%SZd&fFZ2fC2yj",
+    "large-v3": b"ABzY8gWO1E0{>%R7(9S+Kn!D~%ngiGaR?*L!iJG9p-nab0JQ=-{D1-g00",
+    "large": b"ABzY8gWO1E0{>%R7(9S+Kn!D~%ngiGaR?*L!iJG9p-nab0JQ=-{D1-g00",
+    "large-v3-turbo": b"ABzY8j^C+e0{>%RARaKHP%t(lGR*)0g!tONPyhe`",
+    "turbo": b"ABzY8j^C+e0{>%RARaKHP%t(lGR*)0g!tONPyhe`",
+}
+
+
+def _download(url: str, root: str, in_memory: bool) -> Union[bytes, str]:
+    os.makedirs(root, exist_ok=True)
+
+    expected_sha256 = url.split("/")[-2]
+    download_target = os.path.join(root, os.path.basename(url))
+
+    if os.path.exists(download_target) and not os.path.isfile(download_target):
+        raise RuntimeError(f"{download_target} exists and is not a regular file")
+
+    if os.path.isfile(download_target):
+        with open(download_target, "rb") as f:
+            model_bytes = f.read()
+        if hashlib.sha256(model_bytes).hexdigest() == expected_sha256:
+            return model_bytes if in_memory else download_target
+        else:
+            warnings.warn(
+                f"{download_target} exists, but the SHA256 checksum does not match; re-downloading the file"
+            )
+
+    with urllib.request.urlopen(url) as source, open(download_target, "wb") as output:
+        with tqdm(
+            total=int(source.info().get("Content-Length")),
+            ncols=80,
+            unit="iB",
+            unit_scale=True,
+            unit_divisor=1024,
+        ) as loop:
+            while True:
+                buffer = source.read(8192)
+                if not buffer:
+                    break
+
+                output.write(buffer)
+                loop.update(len(buffer))
+
+    model_bytes = open(download_target, "rb").read()
+    if hashlib.sha256(model_bytes).hexdigest() != expected_sha256:
+        raise RuntimeError(
+            "Model has been downloaded but the SHA256 checksum does not not match. Please retry loading the model."
+        )
+
+    return model_bytes if in_memory else download_target
+
+
+def available_models() -> List[str]:
+    """Returns the names of available models"""
+    return list(_MODELS.keys())
+
+
+def load_model(
+    name: str,
+    device: Optional[Union[str, torch.device]] = None,
+    download_root: str = None,
+    in_memory: bool = False,
+) -> Whisper:
+    """
+    Load a Whisper ASR model
+
+    Parameters
+    ----------
+    name : str
+        one of the official model names listed by `whisper.available_models()`, or
+        path to a model checkpoint containing the model dimensions and the model state_dict.
+    device : Union[str, torch.device]
+        the PyTorch device to put the model into
+    download_root: str
+        path to download the model files; by default, it uses "~/.cache/whisper"
+    in_memory: bool
+        whether to preload the model weights into host memory
+
+    Returns
+    -------
+    model : Whisper
+        The Whisper ASR model instance
+    """
+
+    if device is None:
+        device = "cuda" if torch.cuda.is_available() else "cpu"
+    if download_root is None:
+        default = os.path.join(os.path.expanduser("~"), ".cache")
+        whisper_cache = os.path.join(os.getenv("XDG_CACHE_HOME", default), "whisper")
+        sonorus_cache = os.path.join(os.getenv("XDG_CACHE_HOME", default), "sonorus")
+        if os.path.exists(whisper_cache):
+            download_root = whisper_cache
+        else:
+            download_root = sonorus_cache
+
+    if name in _MODELS:
+        checkpoint_file = _download(_MODELS[name], download_root, in_memory)
+        alignment_heads = _ALIGNMENT_HEADS[name]
+    elif os.path.isfile(name):
+        checkpoint_file = open(name, "rb").read() if in_memory else name
+        alignment_heads = None
+    else:
+        raise RuntimeError(
+            f"Model {name} not found; available models = {available_models()}"
+        )
+
+    with (
+        io.BytesIO(checkpoint_file) if in_memory else open(checkpoint_file, "rb")
+    ) as fp:
+        kwargs = {"weights_only": True} if torch.__version__ >= "1.13" else {}
+        checkpoint = torch.load(fp, map_location=device, **kwargs)
+    del checkpoint_file
+
+    dims = ModelDimensions(**checkpoint["dims"])
+    model = Whisper(dims)
+    model.load_state_dict(checkpoint["model_state_dict"])
+
+    if alignment_heads is not None:
+        model.set_alignment_heads(alignment_heads)
+
+    return model.to(device)

sonorus_ai-0.1.0/sonorus/__main__.py

@@ -0,0 +1,3 @@
+from .transcribe import cli
+
+cli()