yapsnap 0.1.0__tar.gz

yapsnap-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

yapsnap-0.1.0/PKG-INFO

@@ -0,0 +1,234 @@
+Metadata-Version: 2.4
+Name: yapsnap
+Version: 0.1.0
+Summary: Snap any video URL or local audio/video into a plaintext transcript. CPU-first, offline, single command.
+Author: yapsnap
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/kouhxp/yapsnap
+Project-URL: Issues, https://github.com/kouhxp/yapsnap/issues
+Keywords: asr,transcription,sherpa-onnx,kroko,yt-dlp,youtube,tiktok,instagram,transcribe
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: sherpa-onnx>=1.10
+Requires-Dist: numpy>=1.23
+Requires-Dist: yt-dlp>=2026.3.17
+Dynamic: license-file
+
+# yapsnap
+
+> **Snap any video URL or audio file into plaintext. No GPU. No cloud. One command.**
+
+![Python](https://img.shields.io/badge/python-3.9+-blue) ![License](https://img.shields.io/badge/license-Apache--2.0-green) ![Platforms](https://img.shields.io/badge/platforms-macOS%20%7C%20Linux%20%7C%20Windows-lightgrey)
+
+```bash
+yapsnap "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
+```
+
+That's it. You get a `.txt` next to your shell, transcribed on your CPU, in less time than it took the video to play.
+
+---
+
+## Why yapsnap
+
+- ⚡ **Fast on CPU.** Streaming Zipformer transducer (Kroko English) chews through audio at several times realtime on a laptop. No CUDA. No M-series-only tricks. Plain old cores.
+- 🌐 **Any video URL, plus local files.** YouTube. X. TikTok. Instagram Reels. Direct `.mp4`/`.mp3` links. Or just point it at a file on disk. yt-dlp handles the fetch, ffmpeg handles the decode, the rest is yours.
+- 📴 **Offline after first run.** ~80 MB model downloads once to your cache and stays there. No API keys. No quotas. Your audio never leaves your machine.
+- 🪶 **One file, three deps.** `sherpa-onnx`, `numpy`, `yt-dlp`. The whole tool is a single Python module.
+- 🗣 **Ten-plus languages.** English out of the box; French, German, Spanish, Italian, Portuguese, Dutch, Swedish, Swiss German, Hebrew, and Turkish are a one-line `--model` swap away. See [Other languages](#other-languages).
+- ⏱ **Sentence-level timestamps when you want them.** `--timestamps` adds `[MM:SS]` per sentence using Kroko's built-in punctuation. Timing stays correct even when you transcribe at 2x.
+
+---
+
+## Quickstart
+
+```bash
+# 1. ffmpeg on PATH (one-time, per OS — see below)
+# 2. Install (from PyPI, or `pip install .` from a clone)
+pip install yapsnap
+
+# 3. Snap something
+yapsnap https://www.tiktok.com/@user/video/7234567890123456789
+yapsnap meeting.mp4 --timestamps
+yapsnap podcast.mp3 -o ~/notes/episode.txt
+```
+
+The first run downloads the model (~80 MB). Every run after is offline.
+
+---
+
+## What it handles
+
+Any URL `yt-dlp` understands works. The big ones:
+
+| Source            | Example                                                 |
+|-------------------|---------------------------------------------------------|
+| YouTube           | `https://www.youtube.com/watch?v=...`                   |
+| YouTube Shorts    | `https://www.youtube.com/shorts/...`                    |
+| X / Twitter       | `https://x.com/user/status/.../video/1`                 |
+| TikTok            | `https://www.tiktok.com/@user/video/...`                |
+| Instagram Reels   | `https://www.instagram.com/reel/.../`                   |
+| Direct media URL  | `https://example.com/clip.mp4`                          |
+
+Plus any local file ffmpeg can decode: `.mp3`, `.mp4`, `.m4a`, `.wav`, `.webm`, `.mov`, `.mkv`, `.aac`, `.opus`, `.ogg`, `.flac`, and friends.
+
+---
+
+## Install
+
+### 1. ffmpeg
+
+| OS      | Command                                                  |
+|---------|----------------------------------------------------------|
+| macOS   | `brew install ffmpeg`                                    |
+| Linux   | `sudo apt install ffmpeg` *or* `sudo dnf install ffmpeg` |
+| Windows | `winget install ffmpeg` *or* `choco install ffmpeg`      |
+
+### 2. yapsnap
+
+From PyPI (recommended):
+
+```bash
+pip install yapsnap
+```
+
+From source:
+
+```bash
+git clone https://github.com/kouhxp/yapsnap
+cd yapsnap
+pip install .
+```
+
+Installs two equivalent commands on your `PATH`: **`yapsnap`** (canonical) and **`transcribe`** (alias, for when the name slips your mind).
+
+---
+
+## Usage
+
+```bash
+# Local file
+yapsnap path/to/audio.mp3
+
+# Any video URL
+yapsnap "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
+
+# Sentence-level timestamps
+yapsnap input.mp4 --timestamps
+
+# Custom output path
+yapsnap input.mp4 -o ./transcripts/talk.txt
+
+# Don't speed audio up before transcribing (default is 1.5x, pitch preserved)
+yapsnap input.mp4 --speed 1.0
+
+# Keep the downloaded audio (URL inputs only)
+yapsnap "https://..." --keep-audio
+```
+
+---
+
+## Output
+
+Plaintext, UTF-8. Default location is `./transcripts/` (created if missing) under the current working directory; override with `-o`. For URL inputs the filename is derived from the video ID (`dQw4w9WgXcQ_transcript.txt`, etc.).
+
+**Without `--timestamps`** — one paragraph of recognized text:
+
+```
+Welcome to the show. Today we're talking about transcription. Let's get started.
+```
+
+**With `--timestamps`** — one sentence per line, timed against the original audio:
+
+```
+[00:00] Welcome to the show.
+[00:03] Today we're talking about transcription.
+[00:08] Let's get started.
+```
+
+Timestamps stay in original-audio time even at `--speed 1.5` or higher.
+
+---
+
+## Flags
+
+| Flag              | Description                                                          |
+|-------------------|----------------------------------------------------------------------|
+| `-o`, `--output`  | Output `.txt` path. Default: `./transcripts/<input>_transcript.txt`. |
+| `--timestamps`    | Emit `[MM:SS] sentence.` lines instead of a single paragraph.        |
+| `--speed`         | Pre-transcription speedup factor, pitch preserved. Default `1.5`.    |
+| `--keep-audio`    | Keep the downloaded audio (URL inputs only).                         |
+| `--model`         | Override the model directory. Also reads `KROKO_MODEL` env var.      |
+
+---
+
+## How it works
+
+1. **Fetch.** If the input is a URL, `yt-dlp` grabs the best audio-only stream to a temp directory. If it's a local path, this step is skipped.
+2. **Decode.** `ffmpeg` pipes the media into 16 kHz mono PCM. The optional `atempo` filter speeds it up without raising pitch.
+3. **Recognize.** A streaming Zipformer2 transducer (Kroko English, INT8 ONNX, ~80 MB) eats the PCM in chunks. CPU-only. Greedy decode.
+4. **Format.** Plain text by default. With `--timestamps`, token timestamps are grouped on `.!?` into sentences and scaled back to original-audio time.
+
+No frame is sent anywhere. No state is kept between runs except the cached model.
+
+---
+
+## Model & cache
+
+The default Kroko English model is downloaded on first run to:
+
+- **macOS** — `~/Library/Caches/yapsnap/`
+- **Linux** — `$XDG_CACHE_HOME/yapsnap/` (or `~/.cache/yapsnap/`)
+- **Windows** — `%LOCALAPPDATA%\yapsnap\`
+
+To use a different streaming transducer (other languages, larger Kroko variants, etc.), point `--model` at a directory containing `encoder(.int8).onnx`, `decoder(.int8).onnx`, `joiner(.int8).onnx`, and `tokens.txt`. Or set `KROKO_MODEL` in your environment.
+
+---
+
+## Other languages
+
+The default model is English, but yapsnap isn't limited to it. To transcribe another language, just download the matching model and point yapsnap at it — no code changes, no reinstall.
+
+Kroko publishes streaming models for a growing list of languages on Hugging Face: <https://huggingface.co/Banafo/Kroko-ASR/tree/main>. As of now that includes:
+
+- Dutch
+- French
+- German
+- Hebrew
+- Italian
+- Portuguese
+- Spanish
+- Swedish
+- Swiss German
+- Turkish
+
+Download the one you need, unpack it into its own folder, and run:
+
+```bash
+# Per-run: pass the model folder explicitly
+yapsnap interview.mp3 --model /path/to/kroko-french
+
+# Or set it once as your default for the session
+export KROKO_MODEL=/path/to/kroko-french
+yapsnap interview.mp3
+```
+
+Each model is single-language, so to work across several languages keep them in separate folders and switch with `--model` (or re-export `KROKO_MODEL`) as you go. Any other sherpa-onnx streaming transducer with the standard `encoder` / `decoder` / `joiner` / `tokens.txt` layout works too, not just the Kroko ones.
+
+---
+
+## Notes & limits
+
+- The default model is **English**. For other languages, download a matching model and pass it with `--model` — see [Other languages](#other-languages) for the current list and instructions.
+- `--speed 1.5` shaves about a third off transcription time with minimal accuracy cost. Try `2.0` if you want it even faster, or `1.0` for noisy, mumbled, or fast-speech sources.
+- Some social-media URLs are geo-locked or login-walled; `yt-dlp` will say so explicitly.
+- This is a streaming model, so timestamps come from token positions in the recognized stream. They're accurate enough for navigation, not for subtitling-grade alignment.
+
+---
+
+## License
+
+Apache-2.0 for this project. The Kroko model is distributed under its own license — see <https://huggingface.co/Banafo/Kroko-ASR>. Powered by [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx) and [yt-dlp](https://github.com/yt-dlp/yt-dlp).

yapsnap-0.1.0/README.md

@@ -0,0 +1,214 @@
+# yapsnap
+
+> **Snap any video URL or audio file into plaintext. No GPU. No cloud. One command.**
+
+![Python](https://img.shields.io/badge/python-3.9+-blue) ![License](https://img.shields.io/badge/license-Apache--2.0-green) ![Platforms](https://img.shields.io/badge/platforms-macOS%20%7C%20Linux%20%7C%20Windows-lightgrey)
+
+```bash
+yapsnap "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
+```
+
+That's it. You get a `.txt` next to your shell, transcribed on your CPU, in less time than it took the video to play.
+
+---
+
+## Why yapsnap
+
+- ⚡ **Fast on CPU.** Streaming Zipformer transducer (Kroko English) chews through audio at several times realtime on a laptop. No CUDA. No M-series-only tricks. Plain old cores.
+- 🌐 **Any video URL, plus local files.** YouTube. X. TikTok. Instagram Reels. Direct `.mp4`/`.mp3` links. Or just point it at a file on disk. yt-dlp handles the fetch, ffmpeg handles the decode, the rest is yours.
+- 📴 **Offline after first run.** ~80 MB model downloads once to your cache and stays there. No API keys. No quotas. Your audio never leaves your machine.
+- 🪶 **One file, three deps.** `sherpa-onnx`, `numpy`, `yt-dlp`. The whole tool is a single Python module.
+- 🗣 **Ten-plus languages.** English out of the box; French, German, Spanish, Italian, Portuguese, Dutch, Swedish, Swiss German, Hebrew, and Turkish are a one-line `--model` swap away. See [Other languages](#other-languages).
+- ⏱ **Sentence-level timestamps when you want them.** `--timestamps` adds `[MM:SS]` per sentence using Kroko's built-in punctuation. Timing stays correct even when you transcribe at 2x.
+
+---
+
+## Quickstart
+
+```bash
+# 1. ffmpeg on PATH (one-time, per OS — see below)
+# 2. Install (from PyPI, or `pip install .` from a clone)
+pip install yapsnap
+
+# 3. Snap something
+yapsnap https://www.tiktok.com/@user/video/7234567890123456789
+yapsnap meeting.mp4 --timestamps
+yapsnap podcast.mp3 -o ~/notes/episode.txt
+```
+
+The first run downloads the model (~80 MB). Every run after is offline.
+
+---
+
+## What it handles
+
+Any URL `yt-dlp` understands works. The big ones:
+
+| Source            | Example                                                 |
+|-------------------|---------------------------------------------------------|
+| YouTube           | `https://www.youtube.com/watch?v=...`                   |
+| YouTube Shorts    | `https://www.youtube.com/shorts/...`                    |
+| X / Twitter       | `https://x.com/user/status/.../video/1`                 |
+| TikTok            | `https://www.tiktok.com/@user/video/...`                |
+| Instagram Reels   | `https://www.instagram.com/reel/.../`                   |
+| Direct media URL  | `https://example.com/clip.mp4`                          |
+
+Plus any local file ffmpeg can decode: `.mp3`, `.mp4`, `.m4a`, `.wav`, `.webm`, `.mov`, `.mkv`, `.aac`, `.opus`, `.ogg`, `.flac`, and friends.
+
+---
+
+## Install
+
+### 1. ffmpeg
+
+| OS      | Command                                                  |
+|---------|----------------------------------------------------------|
+| macOS   | `brew install ffmpeg`                                    |
+| Linux   | `sudo apt install ffmpeg` *or* `sudo dnf install ffmpeg` |
+| Windows | `winget install ffmpeg` *or* `choco install ffmpeg`      |
+
+### 2. yapsnap
+
+From PyPI (recommended):
+
+```bash
+pip install yapsnap
+```
+
+From source:
+
+```bash
+git clone https://github.com/kouhxp/yapsnap
+cd yapsnap
+pip install .
+```
+
+Installs two equivalent commands on your `PATH`: **`yapsnap`** (canonical) and **`transcribe`** (alias, for when the name slips your mind).
+
+---
+
+## Usage
+
+```bash
+# Local file
+yapsnap path/to/audio.mp3
+
+# Any video URL
+yapsnap "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
+
+# Sentence-level timestamps
+yapsnap input.mp4 --timestamps
+
+# Custom output path
+yapsnap input.mp4 -o ./transcripts/talk.txt
+
+# Don't speed audio up before transcribing (default is 1.5x, pitch preserved)
+yapsnap input.mp4 --speed 1.0
+
+# Keep the downloaded audio (URL inputs only)
+yapsnap "https://..." --keep-audio
+```
+
+---
+
+## Output
+
+Plaintext, UTF-8. Default location is `./transcripts/` (created if missing) under the current working directory; override with `-o`. For URL inputs the filename is derived from the video ID (`dQw4w9WgXcQ_transcript.txt`, etc.).
+
+**Without `--timestamps`** — one paragraph of recognized text:
+
+```
+Welcome to the show. Today we're talking about transcription. Let's get started.
+```
+
+**With `--timestamps`** — one sentence per line, timed against the original audio:
+
+```
+[00:00] Welcome to the show.
+[00:03] Today we're talking about transcription.
+[00:08] Let's get started.
+```
+
+Timestamps stay in original-audio time even at `--speed 1.5` or higher.
+
+---
+
+## Flags
+
+| Flag              | Description                                                          |
+|-------------------|----------------------------------------------------------------------|
+| `-o`, `--output`  | Output `.txt` path. Default: `./transcripts/<input>_transcript.txt`. |
+| `--timestamps`    | Emit `[MM:SS] sentence.` lines instead of a single paragraph.        |
+| `--speed`         | Pre-transcription speedup factor, pitch preserved. Default `1.5`.    |
+| `--keep-audio`    | Keep the downloaded audio (URL inputs only).                         |
+| `--model`         | Override the model directory. Also reads `KROKO_MODEL` env var.      |
+
+---
+
+## How it works
+
+1. **Fetch.** If the input is a URL, `yt-dlp` grabs the best audio-only stream to a temp directory. If it's a local path, this step is skipped.
+2. **Decode.** `ffmpeg` pipes the media into 16 kHz mono PCM. The optional `atempo` filter speeds it up without raising pitch.
+3. **Recognize.** A streaming Zipformer2 transducer (Kroko English, INT8 ONNX, ~80 MB) eats the PCM in chunks. CPU-only. Greedy decode.
+4. **Format.** Plain text by default. With `--timestamps`, token timestamps are grouped on `.!?` into sentences and scaled back to original-audio time.
+
+No frame is sent anywhere. No state is kept between runs except the cached model.
+
+---
+
+## Model & cache
+
+The default Kroko English model is downloaded on first run to:
+
+- **macOS** — `~/Library/Caches/yapsnap/`
+- **Linux** — `$XDG_CACHE_HOME/yapsnap/` (or `~/.cache/yapsnap/`)
+- **Windows** — `%LOCALAPPDATA%\yapsnap\`
+
+To use a different streaming transducer (other languages, larger Kroko variants, etc.), point `--model` at a directory containing `encoder(.int8).onnx`, `decoder(.int8).onnx`, `joiner(.int8).onnx`, and `tokens.txt`. Or set `KROKO_MODEL` in your environment.
+
+---
+
+## Other languages
+
+The default model is English, but yapsnap isn't limited to it. To transcribe another language, just download the matching model and point yapsnap at it — no code changes, no reinstall.
+
+Kroko publishes streaming models for a growing list of languages on Hugging Face: <https://huggingface.co/Banafo/Kroko-ASR/tree/main>. As of now that includes:
+
+- Dutch
+- French
+- German
+- Hebrew
+- Italian
+- Portuguese
+- Spanish
+- Swedish
+- Swiss German
+- Turkish
+
+Download the one you need, unpack it into its own folder, and run:
+
+```bash
+# Per-run: pass the model folder explicitly
+yapsnap interview.mp3 --model /path/to/kroko-french
+
+# Or set it once as your default for the session
+export KROKO_MODEL=/path/to/kroko-french
+yapsnap interview.mp3
+```
+
+Each model is single-language, so to work across several languages keep them in separate folders and switch with `--model` (or re-export `KROKO_MODEL`) as you go. Any other sherpa-onnx streaming transducer with the standard `encoder` / `decoder` / `joiner` / `tokens.txt` layout works too, not just the Kroko ones.
+
+---
+
+## Notes & limits
+
+- The default model is **English**. For other languages, download a matching model and pass it with `--model` — see [Other languages](#other-languages) for the current list and instructions.
+- `--speed 1.5` shaves about a third off transcription time with minimal accuracy cost. Try `2.0` if you want it even faster, or `1.0` for noisy, mumbled, or fast-speech sources.
+- Some social-media URLs are geo-locked or login-walled; `yt-dlp` will say so explicitly.
+- This is a streaming model, so timestamps come from token positions in the recognized stream. They're accurate enough for navigation, not for subtitling-grade alignment.
+
+---
+
+## License
+
+Apache-2.0 for this project. The Kroko model is distributed under its own license — see <https://huggingface.co/Banafo/Kroko-ASR>. Powered by [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx) and [yt-dlp](https://github.com/yt-dlp/yt-dlp).

yapsnap-0.1.0/pyproject.toml

@@ -0,0 +1,34 @@
+[build-system]
+requires = ["setuptools>=61", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "yapsnap"
+version = "0.1.0"
+description = "Snap any video URL or local audio/video into a plaintext transcript. CPU-first, offline, single command."
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "Apache-2.0" }
+authors = [{ name = "yapsnap" }]
+keywords = ["asr", "transcription", "sherpa-onnx", "kroko", "yt-dlp", "youtube", "tiktok", "instagram", "transcribe"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+    "Topic :: Multimedia :: Sound/Audio :: Speech",
+]
+dependencies = [
+    "sherpa-onnx>=1.10",
+    "numpy>=1.23",
+    "yt-dlp>=2026.3.17",
+]
+
+[project.urls]
+Homepage = "https://github.com/kouhxp/yapsnap"
+Issues = "https://github.com/kouhxp/yapsnap/issues"
+
+[project.scripts]
+yapsnap = "yapsnap:main"
+transcribe = "yapsnap:main"
+
+[tool.setuptools]
+py-modules = ["yapsnap"]