7 Commits

Author SHA1 Message Date
Li Peng
2d9825aa29 Replace deprecated pytorch methods
- torch.cuda.amp.GradScaler(...) => torch.amp.GradScaler("cuda", ...)
- torch.cuda.amp.autocast(...) => torch.amp.autocast("cuda", ...)
2024-11-27 17:43:17 +08:00
zr_jin
eb132da00d
additional instruction for the grad_scale is too small error (#1550) 2024-03-14 11:33:49 +08:00
zr_jin
242002e0bd
Strengthened style constraints (#1527) 2024-03-04 23:28:04 +08:00
Fangjun Kuang
8136ad775b
Use high_freq -400 in computing fbank features. (#1447)
See also https://github.com/k2-fsa/sherpa-onnx/issues/514
2024-01-04 13:59:32 +08:00
zr_jin
ef658d691e
fixes for init value of diagnostics.TensorDiagnosticOptions (#1269)
* fixes for `diagnostics`

Replace `2 ** 22` with `512` as the default value of `diagnostics.TensorDiagnosticOptions`

also black formatted some scripts

* fixed formatting issues
2023-09-24 17:06:47 +08:00
Fangjun Kuang
7b0afbdc16
Remove cur_batch_idx (#1102) 2023-05-30 14:49:54 +08:00
Wei Kang
bccd20d978
Traning with byte level BPE (TAL_CSASR) (#1033)
* Add byte level bpe tal_csasr recipe

* Minor fixes to decoding and exporting

* Fix prepare.sh

* Update results
2023-05-16 12:44:52 +08:00