Data

Tools

Indexes

Applications

Experiments

Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / microsoft/UniSpeech issues and pull requests

#58 - Weighted Sum for Downstream Tasks

Issue - State: open - Opened by jaeyeonkim99 7 months ago

#57 - [Downstream Tasks] - Diarization using WavLM

Issue - State: open - Opened by ai-nikolai about 1 year ago

#56 - Model checkpoints not available

Issue - State: open - Opened by xulinfan about 1 year ago - 1 comment

#55 - Missing pretrained model for ecapa-tdnn

Issue - State: open - Opened by MichelMarieLamah13 about 1 year ago

#53 - replace blob shared urls with onedirve shared urls

Pull Request - State: closed - Opened by j4ckl1u over 1 year ago

#52 - pip install --require-hashes -r requirements.txt

Issue - State: open - Opened by evelynyhc over 1 year ago - 1 comment

#51 - Update README.md

Pull Request - State: closed - Opened by Sanyuan-Chen over 1 year ago

#50 - The link for the pretrained model is unavailable #UniSpeech-SAT Large

Issue - State: closed - Opened by TKsavy almost 2 years ago - 3 comments

#49 - training wavlm

Issue - State: closed - Opened by dutchsing009 almost 2 years ago

#47 - Problem of cosine similarity computing for speaker verification

Issue - State: open - Opened by Winterspringkle almost 2 years ago - 1 comment

#46 - Speaker verification result

Issue - State: open - Opened by pierfale about 2 years ago - 4 comments

#45 - Bump scipy from 1.7.1 to 1.10.0 in /downstreams/speaker_verification

Pull Request - State: open - Opened by dependabot[bot] about 2 years ago
Labels: dependencies

#43 - Adding Microsoft SECURITY.MD

Pull Request - State: closed - Opened by microsoft-github-policy-service[bot] about 2 years ago

#41 - About finetuning HuBERT_base_ls_960.pt with 1h data

Issue - State: open - Opened by LYPinASR over 2 years ago

#40 - How to use finetune wavlm large model?

Issue - State: open - Opened by haha010508 over 2 years ago - 2 comments

#39 - Change listed source of Flashlight bindings

Pull Request - State: open - Opened by jacobkahn over 2 years ago

#38 - wavlm model for downstream test?

Issue - State: open - Opened by kli017 over 2 years ago

#37 - UniSpeech Model Download

Issue - State: open - Opened by hongfeixue almost 3 years ago

#36 - pre-training detail for Unispeech-SAT

Issue - State: open - Opened by Sreyan88 almost 3 years ago

#34 - Hi, how to calculate the EER or DER

Issue - State: open - Opened by liyunlongaaa almost 3 years ago

#33 - How continue pretrain WavLM for ASR?

Issue - State: open - Opened by cnlinxi almost 3 years ago

#32 - about updated file "unispeech_sat.th"

Issue - State: closed - Opened by zuihaodeyujian almost 3 years ago

#30 - Time stamps in out.rttm file for speaker_diarization

Issue - State: open - Opened by bryant0918 about 3 years ago - 1 comment

#29 - WavLM Inference Error

Issue - State: closed - Opened by bryant0918 about 3 years ago - 2 comments

#28 - Why is my duplicated wavLM results on vox1-o is 30% worse

Issue - State: closed - Opened by AIDman about 3 years ago - 3 comments

#27 - Where is the trainning/test/infer recipe?

Issue - State: closed - Opened by leijue222 about 3 years ago - 1 comment

#25 - The code for computing the relative positional embedding

Issue - State: closed - Opened by mycrazycracy about 3 years ago - 1 comment

#24 - Bug in WavLM?

Issue - State: closed - Opened by OlaWod about 3 years ago - 1 comment

#23 - Pre-processed data missing

Issue - State: open - Opened by umbertomichieli over 3 years ago

#22 - KeyError: "'_name'" Speaker Diarization

Issue - State: closed - Opened by taimoorkhokhar over 3 years ago - 1 comment

#21 - diarization - KeyError: 'embed.weight'

Issue - State: closed - Opened by RuslanSel over 3 years ago - 5 comments

#20 - Unispeech-SAT fairseq code

Issue - State: closed - Opened by RuslanSel over 3 years ago - 4 comments

#19 - release pretrained weights for ILS-SSL

Pull Request - State: closed - Opened by cywang97 over 3 years ago

#18 - Missing recipe/code for speaker verification

Issue - State: closed - Opened by ajinkyakulkarni14 over 3 years ago - 1 comment

#17 - UniSpeech-SAT/speaker_verification: torchaudio version

Issue - State: closed - Opened by msh9184 over 3 years ago - 1 comment

#16 - Formula 6 in paper

Issue - State: closed - Opened by Sreyan88 over 3 years ago - 7 comments

#15 - Huggingface sat model missing tokenizer

Issue - State: closed - Opened by bagustris over 3 years ago - 4 comments

#14 - Is "unispeech_sat.th" wrong ?

Issue - State: closed - Opened by Damien-Da over 3 years ago - 15 comments

#13 - Getting speaker embeddings

Issue - State: closed - Opened by AH289 over 3 years ago - 3 comments

#12 - Update Readme.md

Pull Request - State: closed - Opened by MarkWuNLP almost 4 years ago

#11 - add wavlm

Pull Request - State: closed - Opened by MarkWuNLP almost 4 years ago

#10 - Add links to Unispeech-SAT models on HF

Pull Request - State: closed - Opened by patrickvonplaten almost 4 years ago

#9 - Fine-tuned Unispeech models cannot be downloaded

Issue - State: closed - Opened by patrickvonplaten almost 4 years ago - 1 comment

#8 - add speaker verification demo

Pull Request - State: closed - Opened by czy97 almost 4 years ago - 1 comment

#7 - Speech transcription example?

Issue - State: closed - Opened by johnpaulbin almost 4 years ago - 1 comment

#6 - More details about the output

Issue - State: closed - Opened by AhmedHashish123 almost 4 years ago - 2 comments

#5 - Yuwu1

Pull Request - State: closed - Opened by MarkWuNLP almost 4 years ago

#4 - Access Required for UniSpeech-SAT models

Issue - State: closed - Opened by patrickvonplaten almost 4 years ago - 2 comments

#3 - Release vocab.json for Common Voice

Issue - State: closed - Opened by patrickvonplaten almost 4 years ago - 3 comments

#2 - Merge Unispeech-SAT code

Pull Request - State: closed - Opened by MarkWuNLP almost 4 years ago

#1 - Add UniSpeech-SAT model

Pull Request - State: closed - Opened by MarkWuNLP almost 4 years ago