jacoblincool/smart-whisper

Smart Whisper is a native Node.js addon designed for efficient and streamlined interaction with the whisper.cpp, with automatic model offloading and model manager.

smart-whisper's Issues

Is it possible to have a transcription progress?

Hey.

In whisper.cpp, we have a way to check the progress of the transcription process, for example:

--- transcriptions ---
whisper_print_progress_callback: progress =   8%
--- transcriptions ---
whisper_print_progress_callback: progress =  13%
--- transcriptions ---
whisper_print_progress_callback: progress =  17%
...

Do we have some feature in smart-whisper to check the progress of each transcription?

TIA for any help!

Support Windows

"timestamps" and "offsets" aren't shown in format=detail

Hi.

I have been developing a tool for language learning using smart-whisper, but I have a problem. Basically, I'll need to transcribe word by word from videos/audios, retrieving their offsets and/or timestamps, to repeat listening the word by setting the related time to replay.

Using the example main from the official Whisper.cpp repo, we have the following output:

{
  ...
  "transcription": [
    {
      ...
      "tokens": [
        {
          "text": " And",
          "timestamps": {
            "from": "00:00:00,220",
            "to": "00:00:00,220"
          },
          "offsets": {
            "from": 220,
            "to": 220
          },
          "id": 843,
          "p": 0.651429
        },
        {
          "text": " so",
          "timestamps": {
            "from": "00:00:00,330",
            "to": "00:00:00,450"
          },
          "offsets": {
            "from": 330,
            "to": 450
          },
          "id": 523,
          "p": 0.992918
        },
        ...
        {
          "text": " country",
          "timestamps": {
            "from": "00:00:10,260",
            "to": "00:00:10,990"
          },
          "offsets": {
            "from": 10260,
            "to": 10990
          },
          "id": 1499,
          "p": 0.995465
        }
      ]
    }
  ]
}

So, is it possible to show the timestamps and offsets as below when we configure format as detail in smart-whisper?

TIA for any help!

ERROR: Permission to JacobLinCool/smart-whisper.git denied

Hi.

I have been trying to push a new branch, but I'm receiving the following error:

URL: [email protected]:JacobLinCool/smart-whisper.git
Auth: SSH

smart-whisper % git push --set-upstream origin add-en-models
ERROR: Permission to JacobLinCool/smart-whisper.git denied to silvioprog.
fatal: Could not read from remote repository.

Please make sure you have the correct access rights
and the repository exists.

So, do we have permission to push new branches?

TIA for any help!

[feature request] http server example

Hey, thanks a lot for this amazing and promising project! ❤️

So, it would be nice to add some example, like integrating this with Express, processing uploaded files directly via streaming, instead of uploading and saving the file in local file system.

cheers

Dependency Dashboard

This issue lists Renovate updates and detected dependencies. Read the Dependency Dashboard docs to learn more.

Rate-Limited

These updates are currently rate-limited. Click on a checkbox below to force their creation now.

• fix(deps): update dependency node-addon-api to v7.1.0
• chore(deps): update actions/configure-pages action to v5
• fix(deps): update dependency node-addon-api to v8
• 🔐 Create all rate-limited PRs at once 🔐

Open

These updates have all been created already. Click a checkbox below to force a retry/rebase of any.

• chore(deps): update dependency lint-staged to v15.2.2
• chore(deps): update dependency tsup to v8.0.2
• chore(deps): update dependency tsx to v4.7.2
• chore(deps): update dependency typedoc to v0.25.13
• chore(deps): update dependency @types/node to v20.12.7
• chore(deps): update dependency prettier to v3.2.5
• chore(deps): update dependency typescript to v5.4.5
• chore(deps): update dependency vitest to v1.5.0
• chore(deps): update pnpm to v8.15.7
• chore(deps): update dependency husky to v9
• Click on this checkbox to rebase all open PRs at once

Detected dependencies

github-actions

.github/workflows/docs.yml

• actions/checkout v4
• pnpm/action-setup v2
• actions/configure-pages v3
• actions/upload-pages-artifact v3

.github/workflows/release.yml

• actions/checkout v4
• pnpm/action-setup v2
• changesets/action v1

.github/workflows/test.yml

• actions/checkout v4
• actions/setup-node v4
• actions/setup-python v5
• pnpm/action-setup v2

npm

package.json

• node-addon-api ^7.0.0
• @changesets/changelog-github ^0.5.0
• @changesets/cli ^2.27.1
• @types/node ^20.10.6
• @types/node-wav ^0.0.3
• husky ^8.0.3
• lint-staged ^15.2.0
• node-wav ^0.0.2
• prettier ^3.1.1
• tsup ^8.0.1
• tsx ^4.7.0
• typedoc ^0.25.6
• typescript ^5.3.3
• vitest ^1.1.3
• pnpm 8.10.5

---

• Check this box to trigger a request for Renovate to run again on this repository

Support Result Confidence

[feature request] detected spoken language

Hi.

It would by really useful if we could return the spoken language in the audio, something like this.

So, we would have a property returning en, pt, es etc.

TIA