facebookresearch/fairseq
1
1
Fork 0
mirror of https://github.com/facebookresearch/fairseq.git synced 2024-11-09 02:04:22 +03:00
Code Issues Packages Projects Releases Wiki Activity
c47a9b2eef
fairseq/examples
History
alexeib e6eddd805e make hydra/infer.py work; also dont break if something is removed fro… (#1903) 
Summary:
previously hydra/infer.py did not always work for several reasons which are addressed here

new example usage:

PYTHONPATH=. python examples/speech_recognition/new/infer.py --config-dir examples/speech_recognition/hydra/conf --config-name infer task=audio_pretraining task.data=/path/to/data task.labels=ltr decoding.type=kenlm decoding.lexicon=/path/to/lexicon decoding.lmpath=/path/to/lm dataset.gen_subset=dev_other common_eval.path=/path/to/model.pt decoding.beam=5 decoding.lmweight=2 decoding.wordscore=-1

Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/1903

Reviewed By: arbabu123

Differential Revision: D28700795

Pulled By: alexeib

fbshipit-source-id: 66fe454de49c1bf511b3529ac683f1c8cb08e579
2021-05-26 16:29:10 -07:00
..
adaptive_span Porting adaptive span to fairseq (#1428) 2020-12-14 11:37:18 -08:00
backtranslation Apply black+isort (#1357) 2020-10-18 18:14:51 -07:00
bart move code to .py files, document usage (#1637) 2021-02-24 14:22:55 -08:00
byte_level_bpe Apply black+isort (#1357) 2020-10-18 18:14:51 -07:00
camembert Fix link in CamemBERT readme (#2722) 2020-10-14 09:47:26 -07:00
constrained_decoding Apply black+isort (#1357) 2020-10-18 18:14:51 -07:00
conv_seq2seq Add code for "Pay Less Attention with Lightweight and Dynamic Convolutions" (#473) 2019-01-25 15:40:26 -08:00
criss Add Truncated BPTT example + TransformerXL (#1410) 2020-11-15 19:47:42 -08:00
cross_lingual_language_model Remove --distributed-wrapper (consolidate to --ddp-backend) (#1544) 2021-01-28 14:21:08 -08:00
fast_noisy_channel Fast Noisy Channel Online Decoding for Neural Machine Translation (#1436) 2020-11-17 14:15:33 -08:00
flores101 fixed typo in flores model download link (#1827) 2021-04-28 10:45:36 -07:00
fully_sharded_data_parallel Update README for Fully Sharded Data Parallel (#3331) 2021-03-09 09:40:00 -08:00
gottbert add German RoBERTa model (GottBERT) (#2992) 2020-12-11 19:10:49 -08:00
hubert make hydra/infer.py work; also dont break if something is removed fro… (#1903) 2021-05-26 16:29:10 -07:00
joint_alignment_translation Use the HTTPS URL for cloning fastBPE (#1441) 2019-12-04 07:22:17 -08:00
language_model Remove --distributed-wrapper (consolidate to --ddp-backend) (#1544) 2021-01-28 14:21:08 -08:00
laser LASER training code (#1207) 2021-02-18 03:10:55 -08:00
latent_depth Remove --distributed-wrapper (consolidate to --ddp-backend) (#1544) 2021-01-28 14:21:08 -08:00
layerdrop Miscellaneous fixes (#2193) 2020-05-28 07:29:59 -07:00
linformer refactor RobertaEncoder (#1560) 2021-02-16 15:52:20 -08:00
m2m_100 Update lang-pairs path and add fixed-dictionary for small models (#3084) 2021-02-03 09:01:20 -08:00
mbart Remove --distributed-wrapper (consolidate to --ddp-backend) (#1544) 2021-01-28 14:21:08 -08:00
megatron_11b Apply black+isort (#1357) 2020-10-18 18:14:51 -07:00
multilingual added data scripts and model download links (#1554) 2021-01-12 11:27:11 -08:00
noisychannel Misc fixes (#2786) 2020-10-27 11:26:07 -07:00
nonautoregressive_translation Remove --distributed-wrapper (consolidate to --ddp-backend) (#1544) 2021-01-28 14:21:08 -08:00
paraphraser Apply black+isort (#1357) 2020-10-18 18:14:51 -07:00
pay_less_attention_paper Remove --distributed-wrapper (consolidate to --ddp-backend) (#1544) 2021-01-28 14:21:08 -08:00
pointer_generator Add torch.cuda.amp support (#3460) 2021-05-26 14:39:10 -07:00
quant_noise Remove --distributed-wrapper (consolidate to --ddp-backend) (#1544) 2021-01-28 14:21:08 -08:00
roberta Remove --distributed-wrapper (consolidate to --ddp-backend) (#1544) 2021-01-28 14:21:08 -08:00
rxf Simplify --user-dir and require user-dir module name to be globally unique (#2815) 2020-10-29 17:08:20 -07:00
scaling_nmt Small fixes (#1215) 2020-07-14 14:17:13 -07:00
simultaneous_translation Fix issue with encoder padding mask 2021-04-28 23:23:11 -07:00
speech_recognition make hydra/infer.py work; also dont break if something is removed fro… (#1903) 2021-05-26 16:29:10 -07:00
speech_to_text S2T example bug fixes 2021-05-12 18:04:06 -07:00
stories Misc fixes (#2448) 2020-08-14 10:24:51 -07:00
translation Remove --distributed-wrapper (consolidate to --ddp-backend) (#1544) 2021-01-28 14:21:08 -08:00
translation_moe Remove --distributed-wrapper (consolidate to --ddp-backend) (#1544) 2021-01-28 14:21:08 -08:00
truncated_bptt Move fairseq.distributed_utils -> fairseq.distributed.utils (#1547) 2021-01-28 14:21:09 -08:00
unsupervised_quality_estimation Fixed scripts and instructions for reproducing the results. (#3264) 2021-02-22 14:57:01 -08:00
wav2vec HF Wav2Vec2 Example (#3502) 2021-05-23 16:19:53 -07:00
wmt19 Releasing single pre-finetuning models (#1347) 2020-10-14 14:19:54 -07:00
wmt20 Update WMT20 README.md (#3027) 2020-12-11 12:18:45 -08:00
xlmr typo: Sanskrit* (#2394) 2020-08-04 08:31:11 -07:00
__init__.py Add Truncated BPTT example + TransformerXL (#1410) 2020-11-15 19:47:42 -08:00
.gitignore 0.6.1 -> 0.6.2 (#577) 2019-03-15 10:27:01 -07:00