seamless_communication
seamless_communication copied to clipboard
facebookresearch
Foundational Models for State-of-the-Art Speech and Text Translation
Hello, I'm interested in deploying the seamless_communication project on my own Linux server. Before proceeding, I'd like to ensure that my server meets the necessary hardware requirements. Could you please...
import torchaudio from transformers import AutoProcessor, SeamlessM4Tv2Model processor = AutoProcessor.from_pretrained("facebook/seamless-m4t-v2-large") model = SeamlessM4Tv2Model.from_pretrained("facebook/seamless-m4t-v2-large") fileName="asr.wav" audio, orig_freq = torchaudio.load(fileName) audio = torchaudio.functional.resample(audio, orig_freq=orig_freq, new_freq=16000) audio_inputs = processor(audios=audio, return_tensors="pt") output_tokens = model.generate(**audio_inputs,...
Dear authors and contributors, I wanted to test demo for the new version of SeamlessM4T V2 Large however found out that the microphone cannot be used properly! It'd record voices...
I have tried the following S2TT tasks: | # | Device | Input language | Output language | Result |--|-|-|-----|--- | 1 | `cpu` | Russian | English | ✅...
# - [ ] - - [**_[]()~~~~_**
import json from models import User import requests from super_secret_environment_file import api_key, api_secret from settings import env if env == 'dev': host = "https://staging.bbot.menu" else: host = "https://bbot.menu" new_guest =...
Metadata
Owner
Metadata
Foundational Models for State-of-the-Art Speech and Text Translation