Spaces:
Sleeping
Sleeping
Delete README.md
Browse files
README.md
DELETED
|
@@ -1,84 +0,0 @@
|
|
| 1 |
-
|
| 2 |
-
# Whisper OpenAi Tool Gradio Web implementation
|
| 3 |
-
Whisper is an automatic speech recognition (ASR) system Gradio Web UI Implementation
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
## Installation
|
| 8 |
-
|
| 9 |
-
Install ffmeg on Your Device
|
| 10 |
-
|
| 11 |
-
```bash
|
| 12 |
-
# on Ubuntu or Debian
|
| 13 |
-
sudo apt update
|
| 14 |
-
sudo apt install ffmpeg
|
| 15 |
-
|
| 16 |
-
# on MacOS using Homebrew (https://brew.sh/)
|
| 17 |
-
brew install ffmpeg
|
| 18 |
-
|
| 19 |
-
# on Windows using Chocolatey (https://chocolatey.org/)
|
| 20 |
-
choco install ffmpeg
|
| 21 |
-
|
| 22 |
-
# on Windows using Scoop (https://scoop.sh/)
|
| 23 |
-
scoop install ffmpeg
|
| 24 |
-
```
|
| 25 |
-
|
| 26 |
-
Download Program
|
| 27 |
-
|
| 28 |
-
```bash
|
| 29 |
-
mkdir whisper-sppech2txt
|
| 30 |
-
cd whisper-sppech2txt
|
| 31 |
-
git clone https://github.com/innovatorved/whisper-openai-gradio-implementation.git .
|
| 32 |
-
pip install -r requirements.txt
|
| 33 |
-
```
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
Run Program
|
| 37 |
-
|
| 38 |
-
```bash
|
| 39 |
-
python app.py
|
| 40 |
-
|
| 41 |
-
```
|
| 42 |
-
|
| 43 |
-
## Available models and languages ([Credit](https://github.com/innovatorved/whisper-openai-gradio-implementation/blob/main/README.md))
|
| 44 |
-
|
| 45 |
-
There are five 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 relative speed.
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
| Size | Parameters | English-only model | Multilingual model | Required VRAM | Relative speed |
|
| 49 |
-
|:------:|:----------:|:------------------:|:------------------:|:-------------:|:--------------:|
|
| 50 |
-
| tiny | 39 M | `tiny.en` | `tiny` | ~1 GB | ~32x |
|
| 51 |
-
| base | 74 M | `base.en` | `base` | ~1 GB | ~16x |
|
| 52 |
-
| small | 244 M | `small.en` | `small` | ~2 GB | ~6x |
|
| 53 |
-
| medium | 769 M | `medium.en` | `medium` | ~5 GB | ~2x |
|
| 54 |
-
| large | 1550 M | N/A | `large` | ~10 GB | 1x |
|
| 55 |
-
|
| 56 |
-
For English-only applications, the `.en` models 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.
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
## Screenshots
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
## License
|
| 63 |
-
|
| 64 |
-
[MIT](https://choosealicense.com/licenses/mit/)
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
## Reference
|
| 68 |
-
|
| 69 |
-
- [https://github.com/openai/whisper](https://github.com/openai/whisper)
|
| 70 |
-
- [https://openai.com/blog/whisper/](https://openai.com/blog/whisper/)
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
## Authors
|
| 74 |
-
|
| 75 |
-
- [Ved Gupta](https://www.github.com/innovatorved)
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
## 🚀 About Me
|
| 79 |
-
I'm a Developer i will feel the code then write .
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
## Support
|
| 83 |
-
|
| 84 |
-
For support, email vedgupta@protonmail.com
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|