klaam
klaam copied to clipboard
ARBML
Arabic speech recognition, classification and text-to-speech.
hello everyone , does your implementation used Fastspeech (2s ) or not ? I just want to make sure , Thank you for your work
Hi, I had a look at how to get text from an audio file, but did not get his to extract the voice directly from the audio device through specking....
To organize the code and introduce testing and continuous integration, it would be beneficial to refactor the entire codebase. ## TL;DR - Re-organizing the codebase to follow best practices and...
Hi Ziad, I tried running this script that is available in the readme file to the train the MSA model: `python run_common_voice.py --model_name_or_path="facebook/wav2vec2-large-xlsr-53" --dataset_config_name="ar" --output_dir=/path/to/output/ --cache_dir=/path/to/cache --overwrite_output_dir="yes" --num_train_epochs="1" --per_device_train_batch_size="32" --per_device_eval_batch_size="32"...
Hello Mustafa & Ziad, I have checked your awesome work, which is really helpful to me, but I have a question please ,,I am new to this field, so could...
Is there any project or code that can implement phoneme recognition and alignment for Arabic recordings? Thanks!
i try hard to run the mode or project "offline" locally on pycharm and it not working can anyone give a guide even on colab dont work i dont understand...
I have tested the `klaam/notebook/demo.ipynb` file on Google Colab. It raised an error of **missing modules**. Error Message:  When I install the missing modules manually using `!pip install `...
installing on a python pip environment that was not installed via conda throws an error logs : ```bash Setting conda init... ./install.sh: line 40: conda: command not found ./install.sh: line...
