facebookresearch/seamless_communication issues and pull requests

#513 - final_proj.weight is missing in finetuned model

Issue - State: open - Opened by RRThivyan 13 days ago

#511 - When clicking start streaming, nothing happens.

Issue - State: open - Opened by jgpayne 14 days ago

#510 - ValueError: The input waveform must be two dimensional, but has 102528 dimension(s) instead.

Issue - State: open - Opened by erkaink 26 days ago

#509 - Enhance robustness in post_process_pauserate.py

Pull Request - State: open - Opened by mandlinsarah 28 days ago
Labels: CLA Signed

#508 - seamless-m4t-v2-large can only partially transcribe

Issue - State: closed - Opened by jollyfish-cjy 29 days ago

#507 - sndfile found during cmake but not during build time | MacOs m1 pro

Issue - State: open - Opened by cesarvspr about 1 month ago

#506 - Question regarding MMS and seamless

Issue - State: closed - Opened by HeChengHui about 1 month ago - 5 comments

#505 - Optimized Data Type Handling in PretsselGenerator

Pull Request - State: open - Opened by mandlinsarah about 1 month ago - 2 comments
Labels: CLA Signed

#502 - Use weights_only for load

Pull Request - State: open - Opened by kit1980 about 2 months ago
Labels: CLA Signed

#501 - Streaming S2ST and S2TT Results Remain in English When tgt_lang is Set to 'cmn‘

Issue - State: open - Opened by Zhenzi-Weng about 2 months ago

#500 - Understanding Agent Differences

Issue - State: open - Opened by Zhenzi-Weng about 2 months ago

#499 - standard way to load and save fine-tuned models

Issue - State: open - Opened by ARman-AT about 2 months ago

#498 - Update README.md

Pull Request - State: closed - Opened by alihejazi97 about 2 months ago - 2 comments
Labels: CLA Signed

#497 - packaging conflict

Issue - State: open - Opened by Albert337 about 2 months ago - 1 comment

#496 - Is it possible to fine-tune the model using a fine-tuning method such as LORA?

Issue - State: open - Opened by FHT-hub 2 months ago - 2 comments

#495 - Adding Seamless Nano transcription models

Pull Request - State: closed - Opened by mavlyutovr 2 months ago
Labels: CLA Signed

#494 - how do i finetune my own custom models ?

Issue - State: open - Opened by StephennFernandes 3 months ago

#493 - REDACTED

Issue - State: closed - Opened by Ivorforce 3 months ago - 1 comment

#492 - about tsv file

Issue - State: open - Opened by sunyclj 3 months ago - 1 comment

#491 - streaming_evaluate --task s2st --data-file ../input_1.wav --audio-root-dir ../ --output ./ --tgt-lang eng --expressive --gated-model-dir ./SeamlessExpressive 2024-07-09 12:55:04,014 INFO -- seamless_communication.streaming.agents.unity_pipeline: Loading the UnitY model: seamless_streaming_unity on device=cuda:0, dtype=torch.float16 Killed

Issue - State: open - Opened by sunyclj 3 months ago

#490 - seamless_streaming_unity相关权重自行下载，怎么设置路径

Issue - State: open - Opened by sunyclj 3 months ago - 4 comments

#489 - stdlib.h, error: command '/usr/bin/x86_64-solus-linux-gcc' failed with exit code 1

Issue - State: closed - Opened by FAb7D 3 months ago - 1 comment

#488 - Broken hugging face link

Issue - State: closed - Opened by gokula-krishna-dev 3 months ago

#487 - Cannot install packages

Issue - State: open - Opened by DesouzaSherwin 3 months ago

#486 - MuTox Dataset Annotated Timeline not matching

Issue - State: open - Opened by andyko208 3 months ago

#485 - Does the Seamless encoder participate in parameter updates during X2TT training?

Issue - State: open - Opened by lzl-mt 3 months ago

#484 - Seamless Streaming using microphone input

Issue - State: open - Opened by SherwinDesouza 3 months ago

#483 - Does t2tt and t2ts support real-time streaming generation?

Issue - State: open - Opened by suxuanning 3 months ago - 2 comments

#482 - Norwagian Language Not supported this model

Issue - State: open - Opened by Suryaravi0510 3 months ago

#481 - Fix broken m4t_prepare_dataset guides

Pull Request - State: closed - Opened by kujyp 3 months ago - 3 comments
Labels: CLA Signed

#480 - I am going crazy waiting for the training and fine-tuning code for the SPEECH TO SPEECH task

Issue - State: open - Opened by mc112611 3 months ago

#479 - How use checkpoints that i got from fine-tuning??

Issue - State: closed - Opened by amirmfarzane 3 months ago

#478 - آیا شما توانسته اید یادگیری مدل را اصلاح کنید ؟؟؟

Issue - State: open - Opened by developeranalyser 3 months ago

#477 - Cannot finetune TEXT_TO_SPEECH and SPEECH_TO_SPEECH

Issue - State: open - Opened by yiyibooks 3 months ago - 1 comment

#476 - T2TT not works

Issue - State: open - Opened by zsq2010 3 months ago - 1 comment

#475 - [help] libsndfile is not found | mac m1 proMax, sonoma14.4

Issue - State: open - Opened by OpenSourceCommunityInterface 3 months ago - 2 comments

#474 - $$ FineTune Not Work !

Issue - State: open - Opened by developeranalyser 4 months ago - 1 comment

#473 - tensor format input audio translation error

Issue - State: open - Opened by DengHao97 4 months ago

#472 - Bug in fine-tuning

Issue - State: open - Opened by amirmfarzane 4 months ago - 18 comments

#471 - Cast error details: Unable to cast Python instance of type <class 'pathlib.PosixPath'> to C++ type '?' (#define PYBIND11_DETAILED_ERROR_MESSAGES or compile in debug mode for details)

Issue - State: open - Opened by liuhao0813 4 months ago

#470 - RuntimeError: torchaudio_sox::save_audio_file() Expected a value of type 'str' for argument '_0' but instead found type 'PosixPath'.

Issue - State: open - Opened by liuhao0813 4 months ago

#469 - pip dependency conflict when installing

Issue - State: open - Opened by ivanhe123 4 months ago

#467 - S2S aligned metadata "extension" is a subset of prior metadata release?

Issue - State: open - Opened by arlofaria-cartesia 4 months ago

#466 - Obtain the speech embedding

Issue - State: open - Opened by Sameep-c 4 months ago

#465 - seamless-streaming inference error

Issue - State: closed - Opened by LesterGong 4 months ago

#464 - Reproduciblity/seed

Issue - State: open - Opened by Satyam52 4 months ago

#463 - [ACL2024] DINO-PRETSSEL demo page

Pull Request - State: closed - Opened by mjhwang93 4 months ago
Labels: CLA Signed

#462 - Have anyone face this problem when finetune

Issue - State: open - Opened by xufeiqiong 4 months ago - 1 comment

#461 - How to find out speaker id for certain languages? Is there any reference?

Issue - State: open - Opened by NBStarry 4 months ago

#461 - How to find out speaker id for certain languages? Is there any reference?

Issue - State: open - Opened by NBStarry 4 months ago

#460 - Deployment of Seamless M4T Model - Exporting text.decoder to ONNX or Using torch.jit.trace

Issue - State: open - Opened by HesamAlavian 4 months ago - 1 comment

#458 - Fix potential issue with downloading Gigaspeech

Pull Request - State: closed - Opened by zrthxn 5 months ago
Labels: CLA Signed

#458 - Fix potential issue with downloading Gigaspeech

Pull Request - State: closed - Opened by zrthxn 5 months ago
Labels: CLA Signed

#457 - I can't run bash script for generate dataset for fine-tuning m4t model!

Issue - State: open - Opened by amirmfarzane 5 months ago

#457 - I can't run bash script for generate dataset for fine-tuning m4t model!

Issue - State: open - Opened by amirmfarzane 5 months ago

#456 - Fix finetuning script

Pull Request - State: closed - Opened by mhlakhani 5 months ago - 2 comments
Labels: CLA Signed

#456 - Fix finetuning script

Pull Request - State: closed - Opened by mhlakhani 5 months ago - 2 comments
Labels: CLA Signed

#454 - Is there a person in this desert who can answer me?

Issue - State: open - Opened by developeranalyser 5 months ago - 4 comments

#453 - Documentation for denoising and segmentation

Pull Request - State: closed - Opened by am831 5 months ago
Labels: CLA Signed

#453 - Documentation for denoising and segmentation

Pull Request - State: closed - Opened by am831 5 months ago
Labels: CLA Signed

#452 - text to text not showing even as an option m4t_predict: error: argument --task: invalid choice: 'T2TT' (choose from 'ASR', 'S2ST', 'S2TT')

Issue - State: closed - Opened by gloomiebloomie 5 months ago - 3 comments

#451 - Any plans to release finetuning script for Seamless Streaming?

Issue - State: open - Opened by mussakhojayeva 5 months ago

#451 - Any plans to release finetuning script for Seamless Streaming?

Issue - State: open - Opened by mussakhojayeva 5 months ago

#450 - Train speech language ID classification head

Pull Request - State: open - Opened by am831 5 months ago
Labels: CLA Signed

#449 - Fixed finetuning trainer and enable freezing layers

Pull Request - State: closed - Opened by zrthxn 5 months ago
Labels: CLA Signed

#449 - Fixed finetuning trainer and enable freezing layers

Pull Request - State: closed - Opened by zrthxn 5 months ago
Labels: CLA Signed

#448 - M4T V2 --- Do you know how to teach the TEXT_TO_SPEECH ?? Does that mean no one has done it or you don't want to give me a guide? Thankful

Issue - State: open - Opened by developeranalyser 5 months ago

#448 - M4T V2 --- Do you know how to teach the TEXT_TO_SPEECH ?? Does that mean no one has done it or you don't want to give me a guide? Thankful

Issue - State: open - Opened by developeranalyser 5 months ago - 1 comment

#447 - Language ID Model

Pull Request - State: closed - Opened by zrthxn 5 months ago
Labels: CLA Signed

#447 - Language ID Model

Pull Request - State: closed - Opened by zrthxn 5 months ago
Labels: CLA Signed

#446 - Replace print statements with logger.info()

Pull Request - State: closed - Opened by am831 5 months ago
Labels: CLA Signed

#446 - Replace print statements with logger.info()

Pull Request - State: closed - Opened by am831 5 months ago
Labels: CLA Signed

#445 - Incorrect output for T2TT between English and Japanese on MPS backend.

Issue - State: open - Opened by pettta 5 months ago - 1 comment

#445 - Incorrect output for T2TT between English and Japanese on MPS backend.

Issue - State: open - Opened by pettta 5 months ago - 1 comment

#444 - Sequential Execution of translator.predict() in Multithreaded Environment

Issue - State: open - Opened by lin-xiaosheng 5 months ago

#444 - Sequential Execution of translator.predict() in Multithreaded Environment

Issue - State: open - Opened by lin-xiaosheng 5 months ago

#443 - Enable downloading Gigaspeech

Pull Request - State: closed - Opened by zrthxn 5 months ago
Labels: CLA Signed

#443 - Enable downloading Gigaspeech

Pull Request - State: closed - Opened by zrthxn 5 months ago
Labels: CLA Signed

#442 - After downloading the seamless-m4t-large model file, not able to inference from local files.

Issue - State: open - Opened by navjots121 5 months ago

#442 - After downloading the seamless-m4t-large model file, not able to inference from local files.

Issue - State: open - Opened by navjots121 5 months ago

#441 - Denoise audio with Demucs and pipeline with Transcriber

Pull Request - State: closed - Opened by am831 5 months ago
Labels: CLA Signed

#441 - Denoise audio with Demucs and pipeline with Transcriber

Pull Request - State: closed - Opened by am831 5 months ago
Labels: CLA Signed

#440 - Why the extract_alignment function does not return times?

Issue - State: open - Opened by fishfree 5 months ago

#440 - Why the extract_alignment function does not return times?

Issue - State: open - Opened by fishfree 5 months ago

#438 - Fine Tune Not work for text to speech ???????????????????????????????

Issue - State: closed - Opened by developeranalyser 5 months ago - 2 comments

#438 - Fine Tune Not work for text to speech ???????????????????????????????

Issue - State: closed - Opened by developeranalyser 5 months ago - 2 comments

#434 - Train NEW

Issue - State: closed - Opened by developeranalyser 5 months ago

#434 - Train NEW

Issue - State: closed - Opened by developeranalyser 5 months ago

#433 - The large version will crash out even on Colab A100. Maybe trying using the medium version.

Issue - State: closed - Opened by developeranalyser 5 months ago - 1 comment

#433 - The large version will crash out even on Colab A100. Maybe trying using the medium version.

Issue - State: closed - Opened by developeranalyser 5 months ago - 1 comment

#431 - posible text to speech fineTune ???

Issue - State: closed - Opened by developeranalyser 5 months ago - 2 comments

#431 - posible text to speech fineTune ???

Issue - State: closed - Opened by developeranalyser 5 months ago - 2 comments

#430 - Why?

Issue - State: closed - Opened by developeranalyser 6 months ago

#430 - Why?

Issue - State: closed - Opened by developeranalyser 6 months ago

#426 - NotImplementedError: T2U finetuning implemented only for UnitYT2UModel why??!!

Issue - State: open - Opened by developeranalyser 6 months ago - 4 comments

#425 - .pth file

Issue - State: closed - Opened by developeranalyser 6 months ago

#425 - .pth file

Issue - State: closed - Opened by developeranalyser 6 months ago

#424 - FineTune Errror TEXT_TO_SPEECH Same lang

Issue - State: closed - Opened by developeranalyser 6 months ago - 3 comments

#423 - use orginal .pth or FineTuned .pth

Issue - State: closed - Opened by developeranalyser 6 months ago

#423 - use orginal .pth or FineTuned .pth

Issue - State: closed - Opened by developeranalyser 6 months ago

GitHub / facebookresearch/seamless_communication issues and pull requests