Fangjun Kuang 58a96e5b68

Support exporting to ONNX format (#501) ...

* WIP: Support exporting to ONNX format

* Minor fixes.

* Combine encoder/decoder/joiner into a single file.

* Revert merging three onnx models into a single one.

It's quite time consuming to extract a sub-graph from the combined
model. For instance, it takes more than one hour to extract
the encoder model.

* Update CI to test ONNX models.

* Decode with exported models.

* Fix typos.

* Add more doc.

* Remove ncnn as it is not fully tested yet.

* Fix as_strided for streaming conformer.

2022-08-03 10:30:28 +08:00

..

aidatatang_200zh/ASR

do some changes for export.py (#437)

2022-06-20 14:57:08 +08:00

aishell/ASR

[debug] raise remind when git-lfs not available (#504)

2022-07-28 16:17:49 +08:00

aishell2/ASR

add compile_lg.py for aishell2 recipe (#481)

2022-07-18 14:36:40 +08:00

aishell4/ASR

Update conformer.py for aishell4 (#484)

2022-07-20 21:32:53 +08:00

alimeeting/ASR

do some changes for export.py (#437)

2022-06-20 14:57:08 +08:00

gigaspeech/ASR

Set overwrite=True when extracting features in batches. (#487)

2022-07-29 11:17:19 +08:00

librispeech/ASR

Support exporting to ONNX format (#501)

2022-08-03 10:30:28 +08:00

ptb/LM

fix errors for soft connection (#443)

2022-06-24 10:40:46 +08:00

spgispeech/ASR

Set overwrite=True when extracting features in batches. (#487)

2022-07-29 11:17:19 +08:00

tal_csasr/ASR

[Ready to merge] Pruned transducer stateless5 recipe for tal_csasr (mix Chinese chars and English BPE) (#428)

2022-06-28 11:02:10 +08:00

tedlium3/ASR

do some changes for export.py (#437)

2022-06-20 14:57:08 +08:00

timit/ASR

Fix TIMIT lexicon generation bug (#456)

2022-06-30 19:13:46 +08:00

wenetspeech/ASR

Add other decoding methods (nbest, nbest oracle, nbest LG) for wenetspeech pruned rnnt2 (#482)

2022-07-29 12:03:08 +08:00

yesno/ASR

Replace ChunkedLilcomHdf5Writer with LilcomChunkyWriter. (#411)

2022-06-09 11:18:52 +08:00