🚀
Patrick von Platen PRO
patrickvonplaten
Homepage
None yet
Research interests
Language Generation, NLP, ASR
Organizations
spaces
1
models
91
patrickvonplaten/wav2vec2-large-xlsr-turkish-demo-colab_haha
Updated
patrickvonplaten/wav2vec2-base-timit-demo-colab
Updated
patrickvonplaten/wav2vec2-large-xlsr-turkish-demo-colab
Updated
patrickvonplaten/wav2vec2-large-xlsr-turkish-demo
Updated
•
58
patrickvonplaten/wav2vec2-common_voice-tr-demo-dist
Updated
•
7
patrickvonplaten/wav2vec2-large-repro-960h-libri-120k-steps
Updated
•
0
patrickvonplaten/wav2vec2-pretrained-demo
Updated
•
0
patrickvonplaten/wav2vec2-base-v2
Updated
•
252
patrickvonplaten/wav2vec2-reproduce
Updated
•
4
patrickvonplaten/debug_repo
Updated
•
3
patrickvonplaten/hubert-librispeech-clean-100h-demo-dist
Updated
•
31
patrickvonplaten/wav2vec2-librispeech-clean-100h-demo-dist
Updated
•
8
patrickvonplaten/wav2vec2-common_voice-tr-demo
Updated
•
6
patrickvonplaten/wav2vec2-common_voice-ab-demo
Updated
•
8
patrickvonplaten/tiny-wav2vec2-no-tokenizer
Updated
•
1.95k
patrickvonplaten/run_speech_recognition_ctc
Updated
•
0
patrickvonplaten/wav2vec2_libri
Updated
•
11
patrickvonplaten/common_voice_en
Updated
•
0
patrickvonplaten/wav2vec2-base-100h-2nd-try
Automatic Speech Recognition
•
Updated
•
86
patrickvonplaten/wav2vec2_tiny_random_robust
Automatic Speech Recognition
•
Updated
•
5.44k
patrickvonplaten/s2t-wav2vec2-large-en-de
Updated
•
10
patrickvonplaten/bert2gpt2-cnn_dailymail-fp16
Text2Text Generation
•
Updated
•
193
patrickvonplaten/LibriSpeechTest
Updated
•
0
patrickvonplaten/wav2vec2-german-flax
Updated
•
18
patrickvonplaten/libri_speech_trimmed_10_15s
Updated
•
0
•
1
patrickvonplaten/t5-base-norwegian
Text2Text Generation
•
Updated
•
8
patrickvonplaten/norwegian-gpt2
Updated
•
0
patrickvonplaten/papuGaPT2_correct_vocab_with_0s
Text Generation
•
Updated
•
4
patrickvonplaten/papuGaPT2_correct_vocab_with_infs
Text Generation
•
Updated
•
5
patrickvonplaten/gpt2-als-demo
Text Generation
•
Updated
•
6
patrickvonplaten/opus-mt-en-de
Updated
•
0
patrickvonplaten/hey
Updated
•
0
patrickvonplaten/blubb
Updated
•
0
patrickvonplaten/hubert-dementia-screening
Updated
•
0
patrickvonplaten/clm-als
Updated
•
0
patrickvonplaten/t5-small-norwegian
Text2Text Generation
•
Updated
•
2
patrickvonplaten/wav2vec2_tiny_random
Updated
•
10
patrickvonplaten/english-roberta-base-dummy
Updated
•
0
patrickvonplaten/demo
Updated
•
0
patrickvonplaten/wav2vec2-base-robust
Updated
•
0
patrickvonplaten/wav2vec2-tpu-base
Updated
•
4
patrickvonplaten/t5-als
Text2Text Generation
•
Updated
•
11
patrickvonplaten/als-gpt2
Text Generation
•
Updated
•
22
patrickvonplaten/norwegian-roberta-als
Fill-Mask
•
Updated
•
4
patrickvonplaten/bert-glue-mrpc-test
Text Classification
•
Updated
•
5
patrickvonplaten/norwegian-t5-base
Text2Text Generation
•
Updated
•
8
patrickvonplaten/dummy-t5-test
Text2Text Generation
•
Updated
•
15
patrickvonplaten/t5-pretraining-island
Text2Text Generation
•
Updated
•
4
patrickvonplaten/t5-tiny-random
Text2Text Generation
•
Updated
•
43.1k
patrickvonplaten/wav2vec2-base-libri-100h
Updated
•
120
patrickvonplaten/wav2vec2-base
Updated
•
317
patrickvonplaten/dummy_to_del
Updated
•
2
patrickvonplaten/norwegian-roberta-large
Fill-Mask
•
Updated
•
12
patrickvonplaten/german-roberta-base
Fill-Mask
•
Updated
•
286
patrickvonplaten/bert-base-cased_fine_tuned_glue_mrpc_demo
Text Classification
•
Updated
•
2
patrickvonplaten/test
Text Classification
•
Updated
•
2
patrickvonplaten/reformer-tiny-random
Fill-Mask
•
Updated
•
6
patrickvonplaten/reformer-random
Fill-Mask
•
Updated
•
19
patrickvonplaten/bert-testing
Fill-Mask
•
Updated
•
4
patrickvonplaten/norwegian-roberta-base
Fill-Mask
•
Updated
•
3
patrickvonplaten/tf_tts_fast_speech_2
Updated
•
0
patrickvonplaten/bigbird-large-trivia-itc
Updated
•
0
patrickvonplaten/bigbird-roberta-large
Updated
•
7
patrickvonplaten/wav2vec2-base-timit-demo
Updated
•
287
patrickvonplaten/big-bird-base-trivia-qa
Question Answering
•
Updated
•
22
patrickvonplaten/wav2vec2-base-100h-13K-steps
Updated
•
6
patrickvonplaten/wav2vec2-large-lv60h-100h-2nd-try
Updated
•
7
patrickvonplaten/bigbird-roberta-base-original-attn
Fill-Mask
•
Updated
•
15
patrickvonplaten/led-large-16384-pubmed
Text2Text Generation
•
Updated
•
424
•
1
patrickvonplaten/tryout
Updated
•
0
patrickvonplaten/bert2bert-cnn_dailymail-fp16
Text2Text Generation
•
Updated
•
354
patrickvonplaten/roberta_shared_bbc_xsum
Summarization
•
Updated
•
230
patrickvonplaten/roberta2roberta-share-cnn_dailymail-fp16
Text2Text Generation
•
Updated
•
5
patrickvonplaten/roberta2roberta-cnn_dailymail-fp16
Text2Text Generation
•
Updated
•
210
patrickvonplaten/longformer2roberta-cnn_dailymail-fp16
Text2Text Generation
•
Updated
•
1.92k
•
1
patrickvonplaten/bert2bert_cnn_daily_mail
Summarization
•
Updated
•
95
patrickvonplaten/xprophetnet-decoder-clm-large-uncased
Text Generation
•
Updated
•
4
patrickvonplaten/xprophetnet-large-uncased-standalone
Updated
•
2
patrickvonplaten/prophetnet-large-uncased-standalone
Updated
•
6
patrickvonplaten/prophetnet-decoder-clm-large-uncased
Text Generation
•
Updated
•
30
patrickvonplaten/bert2bert-tiny
Text2Text Generation
•
Updated
•
29
patrickvonplaten/xprophetnet-large-wiki100-cased-xglue-qg_old
Text2Text Generation
•
Updated
•
3
patrickvonplaten/xprophetnet-large-wiki100-cased-xglue-ntg_old
Text2Text Generation
•
Updated
•
3
patrickvonplaten/xprophetnet-large-wiki100-cased_old
Text2Text Generation
•
Updated
•
5
patrickvonplaten/prophetnet-large-uncased-cnndm_old
Text2Text Generation
•
Updated
•
5
patrickvonplaten/prophetnet-large-uncased_old
Text2Text Generation
•
Updated
•
4
patrickvonplaten/rag-sequence-ques-enc-prev
Updated
•
6
patrickvonplaten/rag-sequence-gen-prev
Text2Text Generation
•
Updated
•
3
patrickvonplaten/rag-tiny-random
Updated
•
8
patrickvonplaten/longformer-random-tiny
Updated
•
7.96k
patrickvonplaten/hf-reformer-crime-and-punish
Text Generation
•
Updated
•
33
datasets
6
patrickvonplaten/librispeech_asr_dummy
5.79kLibriSpeech is a corpus of approximately 1000 hours of read English speech with sampling rate of 16 kHz, prepared by Vassil Panayotov with the assistance of Daniel Povey. The data is derived from read audiobooks from the LibriVox project, and has been carefully segmented and aligned. Note that in order to limit the required storage for preparin...
patrickvonplaten/ami_single_headset_segmented_and_chunked
5patrickvonplaten/librispeech_local_dummy
5patrickvonplaten/common_voice_processed_turkish
27patrickvonplaten/librispeech_local
1.83kLibriSpeech is a corpus of approximately 1000 hours of read English speech with sampling rate of 16 kHz, prepared by Vassil Panayotov with the assistance of Daniel Povey. The data is derived from read audiobooks from the LibriVox project, and has been carefully segmented and aligned.87 Note that in order to limit the required storage for prepar...
patrickvonplaten/scientific_papers_dummy
69Scientific papers datasets contains two sets of long and structured documents. The datasets are obtained from ArXiv and PubMed OpenAccess repositories. Both "arxiv" and "pubmed" have two features: - article: the body of the document, pagragraphs seperated by "/n". - abstract: the abstract of the document, pagragraphs seperated by "/n". - ...