dictawhisper 0.0.9 → 0.0.11
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +7 -3
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -6,10 +6,14 @@
|
|
|
6
6
|
|
|
7
7
|
**A local voice journal.** Record in the browser, drop a file, or (optionally) sync a phone folder. Transcribe on your GPU with [faster-whisper](https://github.com/SYSTRAN/faster-whisper). Clean the note with [ollanet](https://ollanet.dev). The `.json` next to each recording is the journal.
|
|
8
8
|
|
|
9
|
-
The npm package is a name hold. Clone this repo
|
|
9
|
+
The npm package (`dictawhisper` `0.0.10`) is a name hold. Clone this repo. There is no installer.
|
|
10
10
|
|
|
11
11
|
**Docs:** [dictawhisper.com/docs](https://dictawhisper.com/docs) · **Site:** [dictawhisper.com](https://dictawhisper.com)
|
|
12
12
|
|
|
13
|
+
## Before you clone
|
|
14
|
+
|
|
15
|
+
Exercised path: Windows, Node 20+, pnpm, Python with [faster-whisper](https://github.com/SYSTRAN/faster-whisper), and an NVIDIA GPU with CUDA. `ffmpeg` is required when denoise is on. macOS and Linux are unverified. CPU mode works and is slow. Cleanup via [ollanet](https://ollanet.dev) is optional.
|
|
16
|
+
|
|
13
17
|
## Install
|
|
14
18
|
|
|
15
19
|
```bash
|
|
@@ -21,7 +25,7 @@ pnpm run doctor
|
|
|
21
25
|
pnpm dev
|
|
22
26
|
```
|
|
23
27
|
|
|
24
|
-
|
|
28
|
+
Ready signal: `pnpm run doctor` exits 0, or only warnings remain. Then open [http://localhost:7777](http://localhost:7777). Point `whisper.python` at the interpreter that has CUDA Whisper. Cleanup host and model are optional; raw transcripts still work.
|
|
25
29
|
|
|
26
30
|
## Quick start
|
|
27
31
|
|
|
@@ -34,7 +38,7 @@ Hit Record, or drag an audio file onto the page. Flags, HTTP, MCP, and `retransc
|
|
|
34
38
|
|
|
35
39
|
## What you get
|
|
36
40
|
|
|
37
|
-
Files are the database. The Whisper model stays loaded. Audio stays on this computer. The inbox is loopback by default; `http.tailscale` puts the same page on your tailnet. Playback follows cleaned paragraphs using Whisper word times.
|
|
41
|
+
Files are the database. Each note is the recording plus a neighboring `.json`. The Whisper model stays loaded. Audio stays on this computer. If you point ollanet at another machine, only the transcript text crosses the network. The inbox is loopback by default; `http.tailscale` puts the same page on your tailnet. Playback follows cleaned paragraphs using Whisper word times. If cleanup is skipped or fails, the inbox shows **raw only** or **cleanup failed**, and **Retry** is available. Transcription itself still needs faster-whisper.
|
|
38
42
|
|
|
39
43
|
<!-- xfacts-nutrition-label -->
|
|
40
44
|
|
package/package.json
CHANGED