Skip to content

Commit

Permalink
Bump up to version 1.5.2
Browse files Browse the repository at this point in the history
  • Loading branch information
zh-plus committed Sep 10, 2024
1 parent b31d499 commit 467970d
Show file tree
Hide file tree
Showing 3 changed files with 27 additions and 10 deletions.
11 changes: 11 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
@@ -1,3 +1,14 @@
## 1.4.2

Code refactoring, documentation updates, and minor bug fixes.

### Other Changes:

- Fixed issue #54.
- Changed the default LLM model to `gpt-4o-mini`.
- Minor improvements on prompts.
- Improve post-optimizations for subtitles.

## 1.4.1

Minor bugfixes and improvements.
Expand Down
24 changes: 15 additions & 9 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,12 @@ e.g. [OpenAI-GPT](https://github.com/openai/openai-python), [Anthropic-Claude](h
```python
lrcer = LRCer(chatbot_model='gemini-1.5-flash')
```
- 2024.9.10: Now openlrc depends on
a [specific commit](https://github.com/SYSTRAN/faster-whisper/commit/d57c5b40b06e59ec44240d93485a95799548af50) of
faster-whisper, which is not published on PyPI. Install it from source:
```shell
pip install "faster-whisper @ https://github.com/SYSTRAN/faster-whisper/archive/d57c5b40b06e59ec44240d93485a95799548af50.tar.gz"
```

## Installation ⚙️

Expand All @@ -66,20 +72,15 @@ e.g. [OpenAI-GPT](https://github.com/openai/openai-python), [Anthropic-Claude](h
`ANTHROPIC_API_KEY`.
- Add your [Google API Key](https://aistudio.google.com/app/apikey) to environment variable `GOOGLE_API_KEY`.

3. Install [PyTorch](https://pytorch.org/get-started/locally/):
```shell
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
```

4. Install latest [fast-whisper](https://github.com/guillaumekln/faster-whisper)
3. Install latest [fast-whisper](https://github.com/guillaumekln/faster-whisper) from source:
```shell
pip install git+https://github.com/guillaumekln/faster-whisper
pip install "faster-whisper @ https://github.com/SYSTRAN/faster-whisper/archive/d57c5b40b06e59ec44240d93485a95799548af50.tar.gz"
```

5. Install [ffmpeg](https://ffmpeg.org/download.html) and add `bin` directory
4. Install [ffmpeg](https://ffmpeg.org/download.html) and add `bin` directory
to your `PATH`.

6. This project can be installed from PyPI:
5. This project can be installed from PyPI:

```shell
pip install openlrc
Expand All @@ -91,6 +92,11 @@ e.g. [OpenAI-GPT](https://github.com/openai/openai-python), [Anthropic-Claude](h
pip install git+https://github.com/zh-plus/openlrc
```

6. Install [PyTorch](https://pytorch.org/get-started/locally/):
```shell
pip install --force-reinstall torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124
```

## Usage 🐍

### GUI
Expand Down
2 changes: 1 addition & 1 deletion pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ in-project = true

[tool.poetry]
name = "openlrc"
version = "1.5.1"
version = "1.5.2"
description = "Transcribe (whisper) and translate (gpt) voice into LRC file."
license = "MIT"
authors = [
Expand Down

0 comments on commit 467970d

Please sign in to comment.