Software Open Access

Transformers: State-of-the-Art Natural Language Processing

Wolf, Thomas; Debut, Lysandre; Sanh, Victor; Chaumond, Julien; Delangue, Clement; Moi, Anthony; Cistac, Perric; Ma, Clara; Jernite, Yacine; Plu, Julien; Xu, Canwen; Le Scao, Teven; Gugger, Sylvain; Drame, Mariama; Lhoest, Quentin; Rush, Alexander M.

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="" xmlns:oai_dc="" xmlns:xsi="" xsi:schemaLocation="">
  <dc:creator>Wolf, Thomas</dc:creator>
  <dc:creator>Debut, Lysandre</dc:creator>
  <dc:creator>Sanh, Victor</dc:creator>
  <dc:creator>Chaumond, Julien</dc:creator>
  <dc:creator>Delangue, Clement</dc:creator>
  <dc:creator>Moi, Anthony</dc:creator>
  <dc:creator>Cistac, Perric</dc:creator>
  <dc:creator>Ma, Clara</dc:creator>
  <dc:creator>Jernite, Yacine</dc:creator>
  <dc:creator>Plu, Julien</dc:creator>
  <dc:creator>Xu, Canwen</dc:creator>
  <dc:creator>Le Scao, Teven</dc:creator>
  <dc:creator>Gugger, Sylvain</dc:creator>
  <dc:creator>Drame, Mariama</dc:creator>
  <dc:creator>Lhoest, Quentin</dc:creator>
  <dc:creator>Rush, Alexander M.</dc:creator>
  <dc:description>New Model additions
WavLM was proposed in WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing by Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, Jian Wu, Long Zhou, Shuo Ren, Yanmin Qian, Yao Qian, Jian Wu, Michael Zeng, Furu Wei.
WavLM sets a new SOTA on the SUPERB benchmark.
Compatible checkpoints can be found on the hub:

Add WavLM by @patrickvonplaten in

Wav2Vec2Phoneme was proposed in Simple and Effective Zero-shot Cross-lingual Phoneme Recognition by Qiantong Xu, Alexei Baevski, Michael Auli.
Wav2Vec2Phoneme allows to do phoneme classification as part of automatic speech recognition

[Wav2Vec2 Phoneme] Let phonemizer lang default to tokenizer's settings by @patrickvonplaten in

Compatible checkpoints can be found on the hub:
Unispeech-SAT was proposed in UNISPEECH-SAT: UNIVERSAL SPEECH REPRESENTATION LEARNING WITH SPEAKER AWARE PRE-TRAINING by Sanyuan Chen, Yu Wu, Chengyi Wang, Zhengyang Chen, Zhuo Chen, Shujie Liu, Jian Wu, Yao Qian, Furu Wei, Jinyu Li, Xiangzhan Yu.
UniSpeech-SAT is especially good at speaker related tasks.
Compatible checkpoints can be found on the hub:
Unispeech was proposed in UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data by Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang.
Three new models are released as part of the ImageGPT integration: ImageGPTModel, ImageGPTForCausalImageModeling, ImageGPTForImageClassification, in PyTorch.
Compatible checkpoints can be found on the hub:
New Tasks
Speaker Diarization and Verification
Wav2Vec2-like architecture now have a speaker diarization and speaker verification head added to their architectures. 
You can try out the new task here:

Add Speaker Diarization and Verification heads by @anton-l in

What's Changed

Move import to avoid circular import by @sgugger in
PoC for conserving old links by @sgugger in
Removes images to put them in a dataset by @LysandreJik in
Post sphinx-clean up and contributing guide updates by @sgugger in
Fix the build documentation job by @sgugger in
Update by @kamalkraj in
Update by @kamalkraj in
Train step fix by @Rocketknight1 in
[Generate] Make generate multi-modal by @patrickvonplaten in
Remove require_datasets testing utility  by @LysandreJik in
[WavLM] Correct position bias computation by @patrickvonplaten in
Fix Perceiver multi GPU test by @NielsRogge in
[WavLM] Layerdrop is not allowed for first layer by @patrickvonplaten in
[Generate] Correct input_ids detection by @patrickvonplaten in
Implement head_mask for Flax BERT and other models copied from BERT by @stancld in
Convert rst to mdx bert by @LysandreJik in
Wav2Vec2 meets phonemes by @patrickvonplaten in
[ImageGPT] Deprecate pixel_values input name to input_ids by @patrickvonplaten in
[Seq2SeqTrainer] Remove model input name hack by @patrickvonplaten in
[WavLM] Fix slow tests by @patrickvonplaten in
Add SD and SV heads for WavLM by @anton-l in
Add an argument to set bucket_cap_mb for PyTorch DDP by @changlan in
Update by @kamalkraj in
Fix dead link to benchmarks.ipynb by @DerekChia in
[Perceiver] Skip multi-gpu tests for now by @patrickvonplaten in
Add 'with torch.no_grad()' to DeBERTa integration test forward pass by @henholm in
Add 'with torch.no_grad()' to BERT integration test forward pass by @henholm in
Add a main_input_name attribute to all models by @sgugger in
[doc] typo by @stas00 in
[logging] implement warning_advice / TRANSFORMERS_NO_ADVISORY_WARNINGS by @stas00 in
Make the onnx submodule init lazy by @sgugger in
Convert docstrings of modeling files by @sgugger in
[Bart] better error message by @patrickvonplaten in
Only create the model card on process 0 by @sgugger in
[ASR example] Improve example + add more examples by @patrickvonplaten in
Fix the value error typo of AdamW's betas' valid values checking by @dourgey in
Add custom stopping_criteria and  logits_processor to generate by @lvwerra in
Replace commit sha by commit url for update jobs by @sgugger in
[examples/summarization] deal with None in data records by @stas00 in
[doc porting] several docs by @stas00 in
Mass conversion of documentation from rst to Markdown by @sgugger in
Fix FLAX_MULTIPLE_CHOICE_SAMPLE typo by @mishig25 in
Fixes in marian doc by @sgugger in
Fix FlaxMarianMTModel return block. by @sgugger in
Fix doc mistakes by @sgugger in
Convert model files from rst to mdx by @LysandreJik in
update the arguments add_prefix_space and trim_offsets in backend_tokenizer.post_processor of RobertaTokenizerFast by @SaulLu in
Feature/fix slow test in mluke by @Ryou0634 in
Updated deberta attention by @guillaume-be in
IterableDatasetShard should use per device batch size instead of real… by @SysuCharon in
Fix Perceiver code example by @NielsRogge in
Fix pytorch image classification example by @mariosasko in
Onnx enable tasks for supported models (part 2) by @michaelbenayoun in
Properly indent return block by @sgugger in

New Contributors

@changlan made their first contribution in
@DerekChia made their first contribution in
@henholm made their first contribution in
@dourgey made their first contribution in
@SysuCharon made their first contribution in

Full Changelog:</dc:description>
  <dc:description>If you use this software, please cite it using these metadata.</dc:description>
  <dc:title>Transformers: State-of-the-Art Natural Language Processing</dc:title>
All versions This version
Views 37,139942
Downloads 1,29325
Data volume 10.0 GB241.7 MB
Unique views 30,889869
Unique downloads 66724


Cite as