-
Certainly! We'll need to modify both the Swift code, the Rust bindings, and the CLI arguments to allow changing the OCR accuracy. Here's how we can do that:
1. First, let's modify the Swift cod…
-
The idea is to generalize `EOF` (end of file) to an arbitrary position in a file. This includes the recognition of these special positions:
1. The EOF (end of file)
2. The EOL (end of **line**), BOL …
-
Hello @MhLiao , my scenario is mostly long text line included. Should I retrain the model by changing the parameter "MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION_W" from 64 to wider, say 128 or 196 (with the…
-
Steps to reproduce
------------------
1. (How do you make the issue happen? Does it happen every time you try it?)
It happens every time I run.
2. (Make sure to go into as much detail as needed …
-
In Chinese speech recognition, the recognized text appears line feed, resulting in incorrect recognition rate
-
你好,我克隆了您的代码,然后运行surface.py 出现`ValueError: not enough values to unpack (expected 3, got 2)`,图片都没有检测结果,这是什么原因?
-
### The problem
Understanding Assist isn't flexible but of course this is an error that occurs during a basic intent recognition.
If you request, "what is bedroom temperature" works but if you reque…
-
- [ ] Try to printout which file causes the problem below
```bash
line 221:9 token recognition error at: '"Vsi na na trg. Crni panter po novem 0,67� \n\n'
line 222:38 token recognition error at: …
-
when specifying word timestamps on a `3m 45s` file, I am seeing a crash
```sh
insanely-fast-whisper --file-name test.wav --timestamp word
```
```python
You are attempting to use Flash Attention 2…
-
```python
import pyttsx3
import speech_recognition as sr
engine = pyttsx3.init("sapi5")
voices = engine.getProperty("voices")
# text to speech
def speak(audio):
engine.say(audio)
…