-
Currently, the language ID based whisper outputs only one language with the top probability:
```rust
fn main() {
let file_path = std::env::args().nth(1).expect("Missing file path argument");
…
-
### What happened?
after selecting Audio file and clicking transcribe he app crashes.
i tried with different audio files
### Steps to reproduce
1) open Vibe
2) select file
3) click transcribe
…
-
基础环境：
windows 11
4070
anaconda
按照官方教程配置换环境，下载了依赖包，下载了ffmpeg也配置了环境变量，但是一运行就显示这个问题，
现在在控制台直接运行 ffmpeg是可以的，不知道什么情况了，求教
```
Adding FFMPEG_PATH to PATH
Traceback (most recent call last):
…
-
hi there, great work! I just wondering that can wavtokenizer be compared with whisper? since the Qwen-audio series uses whisper as an audio encoder, can wavtokenizer be used as an alternative, and whe…
-
### 📦 Environment
Official Preview
### 📌 Version
1.16.2
### 💻 Operating System
Windows
### 🌐 Browser
Chrome
### 🐛 Bug Description
Whisper uses only english but it should also uses other langs…
-
* examples/whisper/export_onnx.md 里写不支持large-size, 请问是芯片本身不支持某些维度的NN,还是这个转换脚本不支持large?
* examples/whisper/python/whisper.py 必须指定task为 en 或zh, 但whisper是有语种识别性能,应该是可以直接输入音频,自动判断音频语种,然后输出对应语种的转写结果。这个是…
-
### Summary
In whisper.cpp, there is a CLI option named `--no-timestamps`. The option is responsible for enabling or disabling the timestamps printing in the transcription result, for example:
- `…
-
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/gradio/routes.py", line 412, in run_predict
output = await app.get_blocks().process_api(
File "/usr/local/li…
-
Just that. I would like to use the Groq API (https://groq.com/), but to do that I had to change the library's code. It's a simple fix, actually.
-
When I tried the example (whisper_stt.py), I got the following error:
Error code: 400 - {'error': {'message': "Invalid file format. Supported formats: ['flac', 'm4a', 'mp3', 'mp4', 'mpeg', 'mpga', 'o…