seamless_communication
seamless_communication copied to clipboard
facebookresearch
Foundational Models for State-of-the-Art Speech and Text Translation
My issue seems very similar to https://github.com/facebookresearch/seamless_communication/issues/83 , but I am using Translator Python API + ASR task. My input is 30 seconds long, and I get about half of...
my python code： import torch import torchaudio from seamless_communication.models.inference import Translator translator = Translator("seamlessM4T_large", "vocoder_36langs", torch.device("cpu"), torch.float32) translated_text, _, _ = translator.predict(subtitle.text, "t2tt", 'cmn', src_lang='eng') and the output： Oh, they...
For Input audio --> output audio language before translating or converting anything
I tried to adapt this snippet of code https://huggingface.co/facebook/seamless-m4t-unity-small-s2t#inference ```python import torchaudio import torch import sounddevice as sd import numpy as np import soundfile as sf audio_input, _ = torchaudio.load("example.wav")...
For example "Oh, Peter." translated to "\,彼得.", "Oh, my god" translated to "\,我的上帝" Almost all of the "Oh" are translated into **\**, making this project almost unusable for Chinese and...
Great work on `seamless_communication` and impressive results! This pull request makes it possible to run `seamless_communication` demo on Replicate (https://replicate.com/cjwbw/seamless_communication) and via API (https://replicate.com/cjwbw/seamless_communication/api)
#### Description When running the `SeamlessM4T_large` model in a Colab notebook, the output becomes repetitive and gibberish. This issue is not present when using the same model in Hugging Face...
I just want to put it on the record here that achieving anything close to what this model provides is prohibitively expensive and prone to technical issues, for any startup....
Hello everyone, I tried to test the reported results on Google Colab, but when I compared the results with [Huggingface space](https://huggingface.co/spaces/facebook/seamless_m4t) using the same inputs, it appeared that there is...
Have same installation issue on a ARM64 with NVIDIA GPU, 16 GB or 64 GB, CUDA 11.2. pip install --verbose --trusted-host fair-package-repo.s3-website-us-east-1.amazonaws.com --extra-index-url http://fair-package-repo.s3-website-us-east-1.amazonaws.com/fairseq2/whl/stable/pt2.0.1/cu118 fairseq2 --verbose Using pip 23.2.1 from...
Metadata
Owner
Metadata
Foundational Models for State-of-the-Art Speech and Text Translation