Remove `utils/documentation_tests.txt` (#25680)

* fix

* fix

* fix

* fix

* fix

* fix

* Apply suggestions from code review
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

---------
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

.github/workflows/doctests.yml

@@ -43,9 +43,13 @@ jobs:
       - name: Show installed libraries and their versions
         run: pip freeze
 
+      - name: Get doctest files
+        run: |
+          $(python3 -c 'from utils.tests_fetcher import get_all_doctest_files; to_test = get_all_doctest_files(); to_test = " ".join(to_test); fp = open("doc_tests.txt", "w"); fp.write(to_test); fp.close()')
+
       - name: Run doctests
         run: |
-          python3 -m pytest -v --make-reports doc_tests_gpu --doctest-modules $(cat utils/documentation_tests.txt) -sv --doctest-continue-on-failure --doctest-glob="*.md"
+          python3 -m pytest -v --make-reports doc_tests_gpu --doctest-modules $(cat doc_tests.txt) -sv --doctest-continue-on-failure --doctest-glob="*.md"
 
       - name: Failure short reports
         if: ${{ failure() }}

utils/documentation_tests.txt

-docs/source/en/autoclass_tutorial.md
-docs/source/en/model_doc/byt5.md
-docs/source/en/model_doc/donut.md
-docs/source/en/model_doc/encoder-decoder.md
-docs/source/en/model_doc/markuplm.md
-docs/source/en/model_doc/speech_to_text.md
-docs/source/en/model_doc/switch_transformers.md
-docs/source/en/model_doc/t5.md
-docs/source/en/model_doc/t5v1.1.md
-docs/source/en/model_doc/tapex.md
-docs/source/en/pipeline_tutorial.md
-docs/source/en/quicktour.md
-docs/source/en/task_summary.md
-docs/source/es/quicktour.md
-src/transformers/generation/configuration_utils.py
-src/transformers/generation/tf_utils.py
-src/transformers/generation/utils.py
-src/transformers/models/albert/configuration_albert.py
-src/transformers/models/albert/modeling_albert.py
-src/transformers/models/albert/modeling_tf_albert.py
-src/transformers/models/albert/tokenization_albert.py
-src/transformers/models/albert/tokenization_albert_fast.py
-src/transformers/models/align/processing_align.py
-src/transformers/models/altclip/processing_altclip.py
-src/transformers/models/audio_spectrogram_transformer/feature_extraction_audio_spectrogram_transformer.py
-src/transformers/models/audio_spectrogram_transformer/modeling_audio_spectrogram_transformer.py
-src/transformers/models/auto/feature_extraction_auto.py
-src/transformers/models/auto/image_processing_auto.py
-src/transformers/models/auto/processing_auto.py
-src/transformers/models/auto/tokenization_auto.py
-src/transformers/models/bark/configuration_bark.py
-src/transformers/models/bark/modeling_bark.py
-src/transformers/models/bark/processing_bark.py
-src/transformers/models/bart/configuration_bart.py
-src/transformers/models/bart/modeling_bart.py
-src/transformers/models/bart/tokenization_bart.py
-src/transformers/models/bart/tokenization_bart_fast.py
-src/transformers/models/barthez/tokenization_barthez.py
-src/transformers/models/barthez/tokenization_barthez_fast.py
-src/transformers/models/bartpho/tokenization_bartpho.py
-src/transformers/models/beit/configuration_beit.py
-src/transformers/models/beit/feature_extraction_beit.py
-src/transformers/models/beit/image_processing_beit.py
-src/transformers/models/beit/modeling_beit.py
-src/transformers/models/bert/configuration_bert.py
-src/transformers/models/bert/modeling_bert.py
-src/transformers/models/bert/modeling_tf_bert.py
-src/transformers/models/bert/tokenization_bert.py
-src/transformers/models/bert/tokenization_bert_fast.py
-src/transformers/models/bert/tokenization_bert_tf.py
-src/transformers/models/bert_generation/configuration_bert_generation.py
-src/transformers/models/bert_generation/tokenization_bert_generation.py
-src/transformers/models/bert_japanese/tokenization_bert_japanese.py
-src/transformers/models/bertweet/tokenization_bertweet.py
-src/transformers/models/big_bird/configuration_big_bird.py
-src/transformers/models/big_bird/modeling_big_bird.py
-src/transformers/models/big_bird/tokenization_big_bird.py
-src/transformers/models/big_bird/tokenization_big_bird_fast.py
-src/transformers/models/bigbird_pegasus/configuration_bigbird_pegasus.py
-src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py
-src/transformers/models/biogpt/tokenization_biogpt.py
-src/transformers/models/bit/image_processing_bit.py
-src/transformers/models/blenderbot/configuration_blenderbot.py
-src/transformers/models/blenderbot/modeling_blenderbot.py
-src/transformers/models/blenderbot/tokenization_blenderbot.py
-src/transformers/models/blenderbot/tokenization_blenderbot_fast.py
-src/transformers/models/blenderbot_small/configuration_blenderbot_small.py
-src/transformers/models/blenderbot_small/modeling_blenderbot_small.py
-src/transformers/models/blenderbot_small/tokenization_blenderbot_small.py
-src/transformers/models/blenderbot_small/tokenization_blenderbot_small_fast.py
-src/transformers/models/blip/image_processing_blip.py
-src/transformers/models/blip/modeling_blip.py
-src/transformers/models/blip/modeling_tf_blip.py
-src/transformers/models/blip/processing_blip.py
-src/transformers/models/blip_2/processing_blip_2.py
-src/transformers/models/bloom/configuration_bloom.py
-src/transformers/models/bloom/tokenization_bloom_fast.py
-src/transformers/models/bridgetower/image_processing_bridgetower.py
-src/transformers/models/bridgetower/processing_bridgetower.py
-src/transformers/models/byt5/tokenization_byt5.py
-src/transformers/models/camembert/configuration_camembert.py
-src/transformers/models/camembert/tokenization_camembert.py
-src/transformers/models/camembert/tokenization_camembert_fast.py
-src/transformers/models/canine/configuration_canine.py
-src/transformers/models/canine/modeling_canine.py
-src/transformers/models/canine/tokenization_canine.py
-src/transformers/models/chinese_clip/feature_extraction_chinese_clip.py
-src/transformers/models/chinese_clip/image_processing_chinese_clip.py
-src/transformers/models/chinese_clip/processing_chinese_clip.py
-src/transformers/models/clap/configuration_clap.py
-src/transformers/models/clap/feature_extraction_clap.py
-src/transformers/models/clap/modeling_clap.py
-src/transformers/models/clap/processing_clap.py
-src/transformers/models/clip/configuration_clip.py
-src/transformers/models/clip/feature_extraction_clip.py
-src/transformers/models/clip/image_processing_clip.py
-src/transformers/models/clip/processing_clip.py
-src/transformers/models/clip/tokenization_clip.py
-src/transformers/models/clip/tokenization_clip_fast.py
-src/transformers/models/clipseg/modeling_clipseg.py
-src/transformers/models/clipseg/processing_clipseg.py
-src/transformers/models/codegen/configuration_codegen.py
-src/transformers/models/codegen/tokenization_codegen.py
-src/transformers/models/codegen/tokenization_codegen_fast.py
-src/transformers/models/conditional_detr/configuration_conditional_detr.py
-src/transformers/models/conditional_detr/feature_extraction_conditional_detr.py
-src/transformers/models/conditional_detr/image_processing_conditional_detr.py
-src/transformers/models/conditional_detr/modeling_conditional_detr.py
-src/transformers/models/convbert/configuration_convbert.py
-src/transformers/models/convbert/tokenization_convbert.py
-src/transformers/models/convbert/tokenization_convbert_fast.py
-src/transformers/models/convnext/configuration_convnext.py
-src/transformers/models/convnext/feature_extraction_convnext.py
-src/transformers/models/convnext/image_processing_convnext.py
-src/transformers/models/convnext/modeling_convnext.py
-src/transformers/models/cpm/tokenization_cpm.py
-src/transformers/models/cpm/tokenization_cpm_fast.py
-src/transformers/models/ctrl/configuration_ctrl.py
-src/transformers/models/ctrl/modeling_ctrl.py
-src/transformers/models/ctrl/tokenization_ctrl.py
-src/transformers/models/cvt/configuration_cvt.py
-src/transformers/models/cvt/modeling_cvt.py
-src/transformers/models/data2vec/configuration_data2vec_audio.py
-src/transformers/models/data2vec/configuration_data2vec_text.py
-src/transformers/models/data2vec/configuration_data2vec_vision.py
-src/transformers/models/data2vec/modeling_data2vec_audio.py
-src/transformers/models/data2vec/modeling_data2vec_vision.py
-src/transformers/models/deberta/configuration_deberta.py
-src/transformers/models/deberta/modeling_deberta.py
-src/transformers/models/deberta/tokenization_deberta.py
-src/transformers/models/deberta/tokenization_deberta_fast.py
-src/transformers/models/deberta_v2/configuration_deberta_v2.py
-src/transformers/models/deberta_v2/modeling_deberta_v2.py
-src/transformers/models/deberta_v2/tokenization_deberta_v2.py
-src/transformers/models/deberta_v2/tokenization_deberta_v2_fast.py
-src/transformers/models/decision_transformer/configuration_decision_transformer.py
-src/transformers/models/deformable_detr/configuration_deformable_detr.py
-src/transformers/models/deformable_detr/feature_extraction_deformable_detr.py
-src/transformers/models/deformable_detr/image_processing_deformable_detr.py
-src/transformers/models/deformable_detr/modeling_deformable_detr.py
-src/transformers/models/deit/configuration_deit.py
-src/transformers/models/deit/feature_extraction_deit.py
-src/transformers/models/deit/image_processing_deit.py
-src/transformers/models/deit/modeling_deit.py
-src/transformers/models/deit/modeling_tf_deit.py
-src/transformers/models/deta/configuration_deta.py
-src/transformers/models/deta/image_processing_deta.py
-src/transformers/models/deta/modeling_deta.py
-src/transformers/models/detr/configuration_detr.py
-src/transformers/models/detr/feature_extraction_detr.py
-src/transformers/models/detr/image_processing_detr.py
-src/transformers/models/detr/modeling_detr.py
-src/transformers/models/dinat/configuration_dinat.py
-src/transformers/models/dinat/modeling_dinat.py
-src/transformers/models/distilbert/configuration_distilbert.py
-src/transformers/models/distilbert/tokenization_distilbert.py
-src/transformers/models/distilbert/tokenization_distilbert_fast.py
-src/transformers/models/donut/feature_extraction_donut.py
-src/transformers/models/donut/image_processing_donut.py
-src/transformers/models/donut/processing_donut.py
-src/transformers/models/dpr/configuration_dpr.py
-src/transformers/models/dpr/tokenization_dpr.py
-src/transformers/models/dpr/tokenization_dpr_fast.py
-src/transformers/models/dpt/feature_extraction_dpt.py
-src/transformers/models/dpt/image_processing_dpt.py
-src/transformers/models/dpt/modeling_dpt.py
-src/transformers/models/efficientformer/image_processing_efficientformer.py
-src/transformers/models/efficientformer/modeling_tf_efficientformer.py
-src/transformers/models/efficientnet/image_processing_efficientnet.py
-src/transformers/models/electra/configuration_electra.py
-src/transformers/models/electra/modeling_electra.py
-src/transformers/models/electra/modeling_tf_electra.py
-src/transformers/models/electra/tokenization_electra.py
-src/transformers/models/electra/tokenization_electra_fast.py
-src/transformers/models/encodec/feature_extraction_encodec.py
-src/transformers/models/encodec/modeling_encodec.py
-src/transformers/models/ernie/configuration_ernie.py
-src/transformers/models/ernie_m/configuration_ernie_m.py
-src/transformers/models/ernie_m/modeling_ernie_m.py
-src/transformers/models/ernie_m/tokenization_ernie_m.py
-src/transformers/models/esm/tokenization_esm.py
-src/transformers/models/flaubert/tokenization_flaubert.py
-src/transformers/models/flava/configuration_flava.py
-src/transformers/models/flava/feature_extraction_flava.py
-src/transformers/models/flava/image_processing_flava.py
-src/transformers/models/flava/processing_flava.py
-src/transformers/models/fnet/configuration_fnet.py
-src/transformers/models/fnet/tokenization_fnet.py
-src/transformers/models/fnet/tokenization_fnet_fast.py
-src/transformers/models/fsmt/configuration_fsmt.py
-src/transformers/models/fsmt/tokenization_fsmt.py
-src/transformers/models/funnel/tokenization_funnel.py
-src/transformers/models/funnel/tokenization_funnel_fast.py
-src/transformers/models/git/modeling_git.py
-src/transformers/models/git/processing_git.py
-src/transformers/models/glpn/feature_extraction_glpn.py
-src/transformers/models/glpn/image_processing_glpn.py
-src/transformers/models/glpn/modeling_glpn.py
-src/transformers/models/gpt2/configuration_gpt2.py
-src/transformers/models/gpt2/modeling_gpt2.py
-src/transformers/models/gpt2/tokenization_gpt2.py
-src/transformers/models/gpt2/tokenization_gpt2_fast.py
-src/transformers/models/gpt2/tokenization_gpt2_tf.py
-src/transformers/models/gpt_neo/configuration_gpt_neo.py
-src/transformers/models/gpt_neox/configuration_gpt_neox.py
-src/transformers/models/gpt_neox/tokenization_gpt_neox_fast.py
-src/transformers/models/gpt_neox_japanese/configuration_gpt_neox_japanese.py
-src/transformers/models/gpt_neox_japanese/tokenization_gpt_neox_japanese.py
-src/transformers/models/gpt_sw3/tokenization_gpt_sw3.py
-src/transformers/models/gptj/modeling_gptj.py
-src/transformers/models/gptsan_japanese/tokenization_gptsan_japanese.py
-src/transformers/models/groupvit/modeling_groupvit.py
-src/transformers/models/groupvit/modeling_tf_groupvit.py
-src/transformers/models/herbert/tokenization_herbert.py
-src/transformers/models/herbert/tokenization_herbert_fast.py
-src/transformers/models/hubert/modeling_hubert.py
-src/transformers/models/imagegpt/configuration_imagegpt.py
-src/transformers/models/imagegpt/feature_extraction_imagegpt.py
-src/transformers/models/imagegpt/image_processing_imagegpt.py
-src/transformers/models/imagegpt/modeling_imagegpt.py
-src/transformers/models/jukebox/tokenization_jukebox.py
-src/transformers/models/jukebox/tokenization_jukebox.py
-src/transformers/models/layoutlm/configuration_layoutlm.py
-src/transformers/models/layoutlm/modeling_layoutlm.py
-src/transformers/models/layoutlm/modeling_tf_layoutlm.py
-src/transformers/models/layoutlm/tokenization_layoutlm.py
-src/transformers/models/layoutlm/tokenization_layoutlm_fast.py
-src/transformers/models/layoutlmv2/configuration_layoutlmv2.py
-src/transformers/models/layoutlmv2/feature_extraction_layoutlmv2.py
-src/transformers/models/layoutlmv2/image_processing_layoutlmv2.py
-src/transformers/models/layoutlmv2/modeling_layoutlmv2.py
-src/transformers/models/layoutlmv2/processing_layoutlmv2.py
-src/transformers/models/layoutlmv2/tokenization_layoutlmv2.py
-src/transformers/models/layoutlmv2/tokenization_layoutlmv2_fast.py
-src/transformers/models/layoutlmv3/configuration_layoutlmv3.py
-src/transformers/models/layoutlmv3/feature_extraction_layoutlmv3.py
-src/transformers/models/layoutlmv3/image_processing_layoutlmv3.py
-src/transformers/models/layoutlmv3/modeling_layoutlmv3.py
-src/transformers/models/layoutlmv3/modeling_tf_layoutlmv3.py
-src/transformers/models/layoutlmv3/processing_layoutlmv3.py
-src/transformers/models/layoutlmv3/tokenization_layoutlmv3.py
-src/transformers/models/layoutlmv3/tokenization_layoutlmv3_fast.py
-src/transformers/models/layoutxlm/processing_layoutxlm.py
-src/transformers/models/layoutxlm/tokenization_layoutxlm.py
-src/transformers/models/layoutxlm/tokenization_layoutxlm_fast.py
-src/transformers/models/led/tokenization_led.py
-src/transformers/models/led/tokenization_led_fast.py
-src/transformers/models/levit/configuration_levit.py
-src/transformers/models/levit/feature_extraction_levit.py
-src/transformers/models/levit/image_processing_levit.py
-src/transformers/models/lilt/modeling_lilt.py
-src/transformers/models/llama/tokenization_llama.py
-src/transformers/models/longformer/modeling_longformer.py
-src/transformers/models/longformer/modeling_tf_longformer.py
-src/transformers/models/longformer/tokenization_longformer.py
-src/transformers/models/longformer/tokenization_longformer_fast.py
-src/transformers/models/longt5/modeling_longt5.py
-src/transformers/models/luke/tokenization_luke.py
-src/transformers/models/lxmert/tokenization_lxmert.py
-src/transformers/models/lxmert/tokenization_lxmert_fast.py
-src/transformers/models/m2m_100/configuration_m2m_100.py
-src/transformers/models/m2m_100/tokenization_m2m_100.py
-src/transformers/models/marian/modeling_marian.py
-src/transformers/models/marian/tokenization_marian.py
-src/transformers/models/markuplm/modeling_markuplm.py
-src/transformers/models/markuplm/processing_markuplm.py
-src/transformers/models/markuplm/tokenization_markuplm.py
-src/transformers/models/markuplm/tokenization_markuplm_fast.py
-src/transformers/models/mask2former/configuration_mask2former.py
-src/transformers/models/mask2former/image_processing_mask2former.py
-src/transformers/models/mask2former/modeling_mask2former.py
-src/transformers/models/maskformer/configuration_maskformer.py
-src/transformers/models/maskformer/feature_extraction_maskformer.py
-src/transformers/models/maskformer/image_processing_maskformer.py
-src/transformers/models/maskformer/modeling_maskformer.py
-src/transformers/models/mbart/configuration_mbart.py
-src/transformers/models/mbart/modeling_mbart.py
-src/transformers/models/mbart/modeling_tf_mbart.py
-src/transformers/models/mbart/tokenization_mbart.py
-src/transformers/models/mbart/tokenization_mbart_fast.py
-src/transformers/models/mbart50/tokenization_mbart50.py
-src/transformers/models/mbart50/tokenization_mbart50_fast.py
-src/transformers/models/megatron_bert/configuration_megatron_bert.py
-src/transformers/models/mgp_str/processing_mgp_str.py
-src/transformers/models/mgp_str/tokenization_mgp_str.py
-src/transformers/models/mluke/tokenization_mluke.py
-src/transformers/models/mobilebert/configuration_mobilebert.py
-src/transformers/models/mobilebert/modeling_mobilebert.py
-src/transformers/models/mobilebert/modeling_tf_mobilebert.py
-src/transformers/models/mobilebert/tokenization_mobilebert.py
-src/transformers/models/mobilebert/tokenization_mobilebert_fast.py
-src/transformers/models/mobilenet_v1/feature_extraction_mobilenet_v1.py
-src/transformers/models/mobilenet_v1/image_processing_mobilenet_v1.py
-src/transformers/models/mobilenet_v1/modeling_mobilenet_v1.py
-src/transformers/models/mobilenet_v2/feature_extraction_mobilenet_v2.py
-src/transformers/models/mobilenet_v2/image_processing_mobilenet_v2.py
-src/transformers/models/mobilenet_v2/modeling_mobilenet_v2.py
-src/transformers/models/mobilevit/feature_extraction_mobilevit.py
-src/transformers/models/mobilevit/image_processing_mobilevit.py
-src/transformers/models/mobilevit/modeling_mobilevit.py
-src/transformers/models/mobilevit/modeling_tf_mobilevit.py
-src/transformers/models/mobilevitv2/configuration_mobilevitv2.py
-src/transformers/models/mobilevitv2/modeling_mobilevitv2.py
-src/transformers/models/mpnet/tokenization_mpnet.py
-src/transformers/models/mpnet/tokenization_mpnet_fast.py
-src/transformers/models/musicgen/configuration_musicgen.py
-src/transformers/models/musicgen/modeling_musicgen.py
-src/transformers/models/musicgen/processing_musicgen.py
-src/transformers/models/mvp/configuration_mvp.py
-src/transformers/models/mvp/tokenization_mvp.py
-src/transformers/models/mvp/tokenization_mvp_fast.py
-src/transformers/models/nat/configuration_nat.py
-src/transformers/models/nat/modeling_nat.py
-src/transformers/models/nezha/configuration_nezha.py
-src/transformers/models/nllb/tokenization_nllb.py
-src/transformers/models/nllb/tokenization_nllb_fast.py
-src/transformers/models/oneformer/configuration_oneformer.py
-src/transformers/models/oneformer/image_processing_oneformer.py
-src/transformers/models/oneformer/modeling_oneformer.py
-src/transformers/models/oneformer/processing_oneformer.py
-src/transformers/models/openai/configuration_openai.py
-src/transformers/models/openai/tokenization_openai.py
-src/transformers/models/openai/tokenization_openai_fast.py
-src/transformers/models/opt/configuration_opt.py
-src/transformers/models/opt/modeling_opt.py
-src/transformers/models/opt/modeling_tf_opt.py
-src/transformers/models/owlvit/feature_extraction_owlvit.py
-src/transformers/models/owlvit/image_processing_owlvit.py
-src/transformers/models/owlvit/modeling_owlvit.py
-src/transformers/models/owlvit/processing_owlvit.py
-src/transformers/models/pegasus/configuration_pegasus.py
-src/transformers/models/pegasus/modeling_pegasus.py
-src/transformers/models/pegasus/tokenization_pegasus.py
-src/transformers/models/pegasus/tokenization_pegasus_fast.py
-src/transformers/models/pegasus_x/configuration_pegasus_x.py
-src/transformers/models/perceiver/feature_extraction_perceiver.py
-src/transformers/models/perceiver/image_processing_perceiver.py
-src/transformers/models/perceiver/modeling_perceiver.py
-src/transformers/models/perceiver/tokenization_perceiver.py
-src/transformers/models/phobert/tokenization_phobert.py
-src/transformers/models/pix2struct/modeling_pix2struct.py
-src/transformers/models/plbart/configuration_plbart.py
-src/transformers/models/plbart/modeling_plbart.py
-src/transformers/models/plbart/tokenization_plbart.py
-src/transformers/models/poolformer/configuration_poolformer.py
-src/transformers/models/poolformer/feature_extraction_poolformer.py
-src/transformers/models/poolformer/image_processing_poolformer.py
-src/transformers/models/poolformer/modeling_poolformer.py
-src/transformers/models/pop2piano/configuration_pop2piano.py
-src/transformers/models/pop2piano/modeling_pop2piano.py
-src/transformers/models/prophetnet/tokenization_prophetnet.py
-src/transformers/models/rag/tokenization_rag.py
-src/transformers/models/realm/configuration_realm.py
-src/transformers/models/realm/tokenization_realm.py
-src/transformers/models/realm/tokenization_realm_fast.py
-src/transformers/models/reformer/configuration_reformer.py
-src/transformers/models/reformer/modeling_reformer.py
-src/transformers/models/reformer/tokenization_reformer.py
-src/transformers/models/reformer/tokenization_reformer_fast.py
-src/transformers/models/regnet/modeling_regnet.py
-src/transformers/models/regnet/modeling_tf_regnet.py
-src/transformers/models/rembert/tokenization_rembert.py
-src/transformers/models/rembert/tokenization_rembert_fast.py
-src/transformers/models/resnet/configuration_resnet.py
-src/transformers/models/resnet/modeling_resnet.py
-src/transformers/models/resnet/modeling_tf_resnet.py
-src/transformers/models/roberta/configuration_roberta.py
-src/transformers/models/roberta/modeling_roberta.py
-src/transformers/models/roberta/modeling_tf_roberta.py
-src/transformers/models/roberta/tokenization_roberta.py
-src/transformers/models/roberta/tokenization_roberta_fast.py
-src/transformers/models/roberta_prelayernorm/configuration_roberta_prelayernorm.py
-src/transformers/models/roberta_prelayernorm/modeling_roberta_prelayernorm.py
-src/transformers/models/roberta_prelayernorm/modeling_tf_roberta_prelayernorm.py
-src/transformers/models/roc_bert/modeling_roc_bert.py
-src/transformers/models/roc_bert/tokenization_roc_bert.py
-src/transformers/models/roformer/tokenization_roformer.py
-src/transformers/models/roformer/tokenization_roformer_fast.py
-src/transformers/models/roformer/tokenization_utils.py
-src/transformers/models/segformer/feature_extraction_segformer.py
-src/transformers/models/segformer/image_processing_segformer.py
-src/transformers/models/segformer/modeling_segformer.py
-src/transformers/models/segformer/modeling_tf_segformer.py
-src/transformers/models/sew/configuration_sew.py
-src/transformers/models/sew/modeling_sew.py
-src/transformers/models/sew_d/configuration_sew_d.py
-src/transformers/models/sew_d/modeling_sew_d.py
-src/transformers/models/speech_encoder_decoder/modeling_speech_encoder_decoder.py
-src/transformers/models/speech_to_text/configuration_speech_to_text.py
-src/transformers/models/speech_to_text/feature_extraction_speech_to_text.py
-src/transformers/models/speech_to_text/modeling_speech_to_text.py
-src/transformers/models/speech_to_text/processing_speech_to_text.py
-src/transformers/models/speech_to_text/tokenization_speech_to_text.py
-src/transformers/models/speech_to_text_2/configuration_speech_to_text_2.py
-src/transformers/models/speech_to_text_2/modeling_speech_to_text_2.py
-src/transformers/models/speech_to_text_2/processing_speech_to_text_2.py
-src/transformers/models/speech_to_text_2/tokenization_speech_to_text_2.py
-src/transformers/models/speecht5/feature_extraction_speecht5.py
-src/transformers/models/speecht5/modeling_speecht5.py
-src/transformers/models/speecht5/processing_speecht5.py
-src/transformers/models/speecht5/tokenization_speecht5.py
-src/transformers/models/splinter/tokenization_splinter.py
-src/transformers/models/splinter/tokenization_splinter_fast.py
-src/transformers/models/squeezebert/configuration_squeezebert.py
-src/transformers/models/squeezebert/tokenization_squeezebert.py
-src/transformers/models/squeezebert/tokenization_squeezebert_fast.py
-src/transformers/models/swin/configuration_swin.py
-src/transformers/models/swin/modeling_swin.py
-src/transformers/models/swin2sr/image_processing_swin2sr.py
-src/transformers/models/swin2sr/modeling_swin2sr.py
-src/transformers/models/swinv2/configuration_swinv2.py
-src/transformers/models/t5/tokenization_t5.py
-src/transformers/models/t5/tokenization_t5_fast.py
-src/transformers/models/table_transformer/modeling_table_transformer.py
-src/transformers/models/tapas/tokenization_tapas.py
-src/transformers/models/time_series_transformer/configuration_time_series_transformer.py
-src/transformers/models/time_series_transformer/modeling_time_series_transformer.py
-src/transformers/models/timesformer/configuration_timesformer.py
-src/transformers/models/timesformer/modeling_timesformer.py
-src/transformers/models/transfo_xl/configuration_transfo_xl.py
-src/transformers/models/transfo_xl/tokenization_transfo_xl.py
-src/transformers/models/trocr/configuration_trocr.py
-src/transformers/models/trocr/modeling_trocr.py
-src/transformers/models/trocr/processing_trocr.py
-src/transformers/models/tvlt/feature_extraction_tvlt.py
-src/transformers/models/tvlt/image_processing_tvlt.py
-src/transformers/models/tvlt/processing_tvlt.py
-src/transformers/models/unispeech/configuration_unispeech.py
-src/transformers/models/unispeech/modeling_unispeech.py
-src/transformers/models/unispeech_sat/modeling_unispeech_sat.py
-src/transformers/models/upernet/modeling_upernet.py
-src/transformers/models/videomae/feature_extraction_videomae.py
-src/transformers/models/videomae/image_processing_videomae.py
-src/transformers/models/videomae/modeling_videomae.py
-src/transformers/models/vilt/feature_extraction_vilt.py
-src/transformers/models/vilt/image_processing_vilt.py
-src/transformers/models/vilt/modeling_vilt.py
-src/transformers/models/vilt/processing_vilt.py
-src/transformers/models/vision_encoder_decoder/configuration_vision_encoder_decoder.py
-src/transformers/models/vision_encoder_decoder/modeling_vision_encoder_decoder.py
-src/transformers/models/vision_text_dual_encoder/configuration_vision_text_dual_encoder.py
-src/transformers/models/vision_text_dual_encoder/modeling_tf_vision_text_dual_encoder.py
-src/transformers/models/vision_text_dual_encoder/processing_vision_text_dual_encoder.py
-src/transformers/models/visual_bert/configuration_visual_bert.py
-src/transformers/models/vit/configuration_vit.py
-src/transformers/models/vit/feature_extraction_vit.py
-src/transformers/models/vit/image_processing_vit.py
-src/transformers/models/vit/modeling_tf_vit.py
-src/transformers/models/vit/modeling_vit.py
-src/transformers/models/vit_hybrid/image_processing_vit_hybrid.py
-src/transformers/models/vit_mae/configuration_vit_mae.py
-src/transformers/models/vit_mae/modeling_vit_mae.py
-src/transformers/models/vit_msn/modeling_vit_msn.py
-src/transformers/models/wav2vec2/configuration_wav2vec2.py
-src/transformers/models/wav2vec2/feature_extraction_wav2vec2.py
-src/transformers/models/wav2vec2/modeling_wav2vec2.py
-src/transformers/models/wav2vec2/processing_wav2vec2.py
-src/transformers/models/wav2vec2/tokenization_wav2vec2.py
-src/transformers/models/wav2vec2_conformer/configuration_wav2vec2_conformer.py
-src/transformers/models/wav2vec2_conformer/modeling_wav2vec2_conformer.py
-src/transformers/models/wav2vec2_phoneme/tokenization_wav2vec2_phoneme.py
-src/transformers/models/wav2vec2_with_lm/processing_wav2vec2_with_lm.py
-src/transformers/models/wavlm/configuration_wavlm.py
-src/transformers/models/wavlm/modeling_wavlm.py
-src/transformers/models/whisper/configuration_whisper.py
-src/transformers/models/whisper/feature_extraction_whisper.py
-src/transformers/models/whisper/modeling_tf_whisper.py
-src/transformers/models/whisper/modeling_whisper.py
-src/transformers/models/whisper/processing_whisper.py
-src/transformers/models/whisper/tokenization_whisper.py
-src/transformers/models/whisper/tokenization_whisper_fast.py
-src/transformers/models/x_clip/modeling_x_clip.py
-src/transformers/models/x_clip/processing_x_clip.py
-src/transformers/models/xglm/tokenization_xglm.py
-src/transformers/models/xglm/tokenization_xglm_fast.py
-src/transformers/models/xlm/configuration_xlm.py
-src/transformers/models/xlm/tokenization_xlm.py
-src/transformers/models/xlm_prophetnet/tokenization_xlm_prophetnet.py
-src/transformers/models/xlm_roberta/configuration_xlm_roberta.py
-src/transformers/models/xlm_roberta/tokenization_xlm_roberta.py
-src/transformers/models/xlm_roberta/tokenization_xlm_roberta_fast.py
-src/transformers/models/xlm_roberta_xl/configuration_xlm_roberta_xl.py
-src/transformers/models/xlnet/configuration_xlnet.py
-src/transformers/models/xlnet/tokenization_xlnet.py
-src/transformers/models/xlnet/tokenization_xlnet_fast.py
-src/transformers/models/xmod/configuration_xmod.py
-src/transformers/models/xmod/modeling_xmod.py
-src/transformers/models/yolos/configuration_yolos.py
-src/transformers/models/yolos/feature_extraction_yolos.py
-src/transformers/models/yolos/image_processing_yolos.py
-src/transformers/models/yolos/modeling_yolos.py
-src/transformers/models/yoso/configuration_yoso.py
-src/transformers/pipelines/
-src/transformers/pipelines/text_to_audio.py
\ No newline at end of file

utils/not_doctested.txt

@@ -194,6 +194,7 @@ docs/source/en/model_doc/phobert.md
 docs/source/en/model_doc/pix2struct.md
 docs/source/en/model_doc/plbart.md
 docs/source/en/model_doc/poolformer.md
+docs/source/en/model_doc/pop2piano.md
 docs/source/en/model_doc/prophetnet.md
 docs/source/en/model_doc/pvt.md
 docs/source/en/model_doc/qdqbert.md
@@ -727,6 +728,10 @@ src/transformers/models/pix2struct/image_processing_pix2struct.py
 src/transformers/models/pix2struct/processing_pix2struct.py
 src/transformers/models/plbart/convert_plbart_original_checkpoint_to_torch.py
 src/transformers/models/poolformer/convert_poolformer_original_to_pytorch.py
+src/transformers/models/pop2piano/convert_pop2piano_weights_to_hf.py
+src/transformers/models/pop2piano/feature_extraction_pop2piano.py
+src/transformers/models/pop2piano/processing_pop2piano.py
+src/transformers/models/pop2piano/tokenization_pop2piano.py
 src/transformers/models/prophetnet/configuration_prophetnet.py
 src/transformers/models/prophetnet/convert_prophetnet_original_pytorch_checkpoint_to_pytorch.py
 src/transformers/models/prophetnet/modeling_prophetnet.py
@@ -785,6 +790,7 @@ src/transformers/models/speech_to_text/modeling_tf_speech_to_text.py
 src/transformers/models/speecht5/configuration_speecht5.py
 src/transformers/models/speecht5/convert_hifigan.py
 src/transformers/models/speecht5/convert_speecht5_original_pytorch_checkpoint_to_pytorch.py
+src/transformers/models/speecht5/number_normalizer.py
 src/transformers/models/splinter/configuration_splinter.py
 src/transformers/models/splinter/modeling_splinter.py
 src/transformers/models/squeezebert/modeling_squeezebert.py
@@ -968,8 +974,10 @@ src/transformers/utils/bitsandbytes.py
 src/transformers/utils/constants.py
 src/transformers/utils/doc.py
 src/transformers/utils/dummy_detectron2_objects.py
+src/transformers/utils/dummy_essentia_and_librosa_and_pretty_midi_and_scipy_and_torch_objects.py
 src/transformers/utils/dummy_flax_objects.py
 src/transformers/utils/dummy_keras_nlp_objects.py
+src/transformers/utils/dummy_music_objects.py
 src/transformers/utils/dummy_pt_objects.py
 src/transformers/utils/dummy_sentencepiece_and_tokenizers_objects.py
 src/transformers/utils/dummy_sentencepiece_objects.py

utils/tests_fetcher.py

@@ -367,6 +367,34 @@ def get_diff_for_doctesting(repo: Repo, base_commit: str, commits: List[str]) ->
     return code_diff
 
 
+def get_all_doctest_files() -> List[str]:
+    """
+    Return the complete list of python and Markdown files on which we run doctest.
+
+    At this moment, we restrict this to only take files from `src/` or `docs/source/en/` that are not in `utils/not_doctested.txt`.
+
+    Returns:
+        `List[str]`: The complete list of Python and Markdown files on which we run doctest.
+    """
+    py_files = [str(x.relative_to(PATH_TO_REPO)) for x in PATH_TO_REPO.glob("**/*.py")]
+    md_files = [str(x.relative_to(PATH_TO_REPO)) for x in PATH_TO_REPO.glob("**/*.md")]
+    test_files_to_run = py_files + md_files
+
+    # only include files in `src` or `docs/source/en/`
+    test_files_to_run = [x for x in test_files_to_run if x.startswith(("src/", "docs/source/en/"))]
+    # not include init files
+    test_files_to_run = [x for x in test_files_to_run if not x.endswith(("__init__.py",))]
+
+    # These are files not doctested yet.
+    with open("utils/not_doctested.txt") as fp:
+        not_doctested = set(fp.read().strip().split("\n"))
+
+    # So far we don't have 100% coverage for doctest. This line will be removed once we achieve 100%.
+    test_files_to_run = [x for x in test_files_to_run if x not in not_doctested]
+
+    return sorted(test_files_to_run)
+
+
 def get_doctest_files(diff_with_last_commit: bool = False) -> List[str]:
     """
     Return a list of python and Markdown files where doc example have been modified between:
@@ -396,26 +424,19 @@ def get_doctest_files(diff_with_last_commit: bool = False) -> List[str]:
             print(f"Parent commit: {commit}")
         test_files_to_run = get_diff_for_doctesting(repo, repo.head.commit, parent_commits)
 
-    # These are files not doctested yet.
-    with open("utils/not_doctested.txt") as fp:
-        not_doctested = set(fp.read().strip().split("\n"))
-    # Do not run slow doctest tests
+    all_test_files_to_run = get_all_doctest_files()
+
+    # Do not run slow doctest tests on CircleCI
     with open("utils/slow_documentation_tests.txt") as fp:
         slow_documentation_tests = set(fp.read().strip().split("\n"))
-
-    # So far we don't have 100% coverage for doctest. This line will be removed once we achieve 100%.
-    test_files_to_run = [x for x in test_files_to_run if x not in not_doctested and x not in slow_documentation_tests]
-
-    # The file `utils/not_doctested.txt` doesn't contain all files that are not doc-tested, so we need more filters.
-    # 1. only include files in `src` or `docs/source/en/`
-    test_files_to_run = [x for x in test_files_to_run if x.startswith(("src/", "docs/source/en/"))]
-    # 2. not include init files
-    test_files_to_run = [x for x in test_files_to_run if not x.endswith(("__init__.py",))]
+    test_files_to_run = [
+        x for x in test_files_to_run if x in all_test_files_to_run and x not in slow_documentation_tests
+    ]
 
     # Make sure we did not end up with a test file that was removed
     test_files_to_run = [f for f in test_files_to_run if (PATH_TO_REPO / f).exists()]
 
-    return test_files_to_run
+    return sorted(test_files_to_run)
 
 
 # (:?^|\n) -> Non-catching group for the beginning of the doc or a new line.