seamless_communication
seamless_communication copied to clipboard
facebookresearch
Foundational Models for State-of-the-Art Speech and Text Translation
I tried to install it in kaggle using the command !pip install -e ./seamless_communication after i cloned the official repo. But there are A LOT of dependency conflicts. ERROR: pip's...
The metadata files in [docs/m4t/seamless_align_README.md](https://github.com/facebookresearch/seamless_communication/blob/main/docs/m4t/seamless_align_README.md) come in several dated revisions. From what I've checked of `enA-ptA` and `enA-esA` at least, it seems like the "extension" from Nov 30 is a...
How do we get the final speech embedding (output of the length adaptor) for SeamlessM4T?
Hi, I am not able to reproduce ASR results after fine-tuning the seamlessM4T_medium. After fine-tuning in the same setting I am getting different results. I tried setting seeds but having...
Just as the title, "vocoder_num_spkrs": 200, there are 200 different speakers. How to find a suitable one for certain language?
#### Description I am currently working on deploying the Seamless M4T model for text-to-text translation on a Triton server. I have successfully exported the `text.encoder` to ONNX and traced it...
As I mentioned, I want to fine-tune the M4T model but I need a sample for that. I couldn't use the `dataset.py` file because some files required for downloading don't...
Hi, I am finetuning the base model to allow text to speech for indic languages that are not supported for output speech support. After finetuning, I can't able to load...
I have built the docker image using: docker build -t seamless . Then I ran the docker container using: docker run --gpus all -p 7860:7860 image_id The UI comes up...
Hello, I am getting the error below and I can't find a solution. Does anyone have an idea of what I should do? I asked ChatGPT, I tried making the...
Metadata
Owner
Metadata
Foundational Models for State-of-the-Art Speech and Text Translation