 Alisamar Husain
|
ba7f6d0725
Fixed finetuning trainer and enable freezing layers (#449)
|
hai 1 ano |
 Alisha Maddy
|
6073b25982
Segment audio with Silero VAD and pipeline with Transcriber (#406)
|
hai 1 ano |
|
Alisha Maddy
|
fed73b6aad
Replace print statements with logger.info() (#446)
|
hai 1 ano |
|
Alisha Maddy
|
ca20aa8a1e
Denoise audio with Demucs and pipeline with Transcriber (#441)
|
hai 1 ano |
|
Alisamar Husain
|
1f254b1074
Enable downloading Gigaspeech (#443)
|
hai 1 ano |
 Ilia Kulikov
|
66054d4278
Update alignment_extractor.py (#439)
|
hai 1 ano |
 David Dale
|
95abd7d350
Indicate the SONAR device in the mutox example and explain the dataset columns (#412)
|
hai 1 ano |
|
Alisamar Husain
|
1971db5dd6
Fix issues in Autocast (#400)
|
hai 1 ano |
|
Alisamar Husain
|
5effa1f2a2
Fix float precision in Finetune CLI (#399)
|
hai 1 ano |
|
Alisamar Husain
|
936b939c1f
Added Spanish langcode mapping (#398)
|
hai 1 ano |
|
Alisamar Husain
|
6e047a9ae1
Enable using `m4t_evaluate` with a Manifest JSON file (#395)
|
hai 1 ano |
 Han Rodríguez
|
75ed7ef2db
Transcriber class (#185)
|
hai 1 ano |
|
David Dale
|
859e0aaf84
fix mutox url (#360)
|
hai 1 ano |
 Ning
|
1862dea5b7
Add back unity lib files (#344)
|
hai 1 ano |
|
Ning
|
fbf6f348f2
Interactive only unity.cpp & Fix warnings (#334)
|
hai 1 ano |
 Pierre Andrews
|
07279891ea
Mutox Classifier Model (#332)
|
hai 1 ano |
|
Ning
|
586eab1367
Update README.md (#333)
|
hai 1 ano |
|
Ning
|
b0415debec
unity.cpp sync (#329)
|
hai 1 ano |
 Ruslan Mavlyutov
|
9f883a6b4f
Adjust M4T example finetuning script to align with seamless_communication/fairseq2 changes in Nov'23 (#326)
|
hai 1 ano |
 Guillaume Wenzek
|
dd67e71317
GGML Allow loading fp16 models, add --mem flag (#320)
|
hai 1 ano |
 Long
|
a9f6fa2c98
Update README.md (#304)
|
hai 1 ano |
|
Guillaume Wenzek
|
c634c446d1
save model as fp16 (#277)
|
hai 1 ano |
 Maha
|
04c54e0e64
Fix HF model sampling_rate in M4T README.md (#295)
|
hai 1 ano |
 Vaibhav Srivastav
|
574019c1f6
Add HF Hub Model card + checkpoint. - Conformer shaw (#288)
|
hai 1 ano |
 Kaushik Ram Sadagopan
|
85b3e0c1ec
Open-sourcing W2v-BERT 2.0 speech encoder. (#286)
|
hai 1 ano |
 yeyinthtoon
|
5807362d14
Remove T2ST task from audio resampling and add ASR and S2TT (#276)
|
hai 1 ano |
 Ovidijus Parsiunas
|
d64d1b738a
Update README.md (#262)
|
hai 1 ano |
 Oheed Imran
|
4a0ce6ae45
Update README.md (#279)
|
hai 1 ano |
|
Kaushik Ram Sadagopan
|
d9cf935f5f
Seamless Tutorial - One-stop shop to learn how to use the entire suite of Seamless models. (#280)
|
hai 1 ano |
|
Maha
|
58796ae188
Inference instructions for M4T (#274)
|
hai 1 ano |
