Karel Vesely
3f2a17ef47
Fixes issue #535 , fix hexa 1-char tokens in ASR output. ( #550 )
...
- Avoid output like : `[' K', '<0x64>', '<0x79>', 'ť', ' a', '<0x75>',
'to', 'bu', '<0x73>', '<0x75>', ... ]` with regular 500 BPE units.
- Don't rewrite 1-char tokens in range [ 0x20 (space) .. 0x7E (tilde) ]
2024-01-26 19:23:20 +08:00
chiiyeh
e7b18a2139
add blank_penalty for online transducer ( #548 )
2024-01-26 12:12:13 +08:00
Fangjun Kuang
e215d0c39a
Fix Byte BPE string results for Python. ( #512 )
...
It ignores invalid UTF8 strings.
2024-01-03 16:03:24 +08:00
Fangjun Kuang
98b67ad850
Fix reading hotwords file for android ( #354 )
2023-10-11 12:20:50 +08:00
Fangjun Kuang
33a5765169
Print a more user-friendly error message when using --hotwords-file. ( #344 )
2023-09-26 11:04:20 +08:00
Fangjun Kuang
552a267c23
Set is_final and start_time for online websocket server. ( #342 )
...
* Set is_final and start_time for online websocket server.
* Convert timestamps to a json array
2023-09-25 15:12:07 +08:00
Wei Kang
47184f9db7
Refactor hotwords，support loading hotwords from file ( #296 )
2023-09-14 19:33:17 +08:00
Fangjun Kuang
a12ebfab22
treat unk as blank ( #299 )
2023-09-07 15:12:29 +08:00
Fangjun Kuang
a0a747a0c0
add endpointing for online websocket server ( #294 )
2023-08-31 14:41:04 +08:00
Fangjun Kuang
6038e2aa62
Support streaming paraformer ( #263 )
2023-08-14 10:32:14 +08:00
frankyoujian
9dcad7e963
Reinitialize context state after Reset stream when using contexts ( #257 )
2023-08-10 14:19:40 +08:00
Fangjun Kuang
79c2ce5dd4
Refactor online recognizer ( #250 )
...
* Refactor online recognizer.
Make it easier to support other streaming models.
Note that it is a breaking change for the Python API.
`sherpa_onnx.OnlineRecognizer()` used before should be
replaced by `sherpa_onnx.OnlineRecognizer.from_transducer()`.
2023-08-09 20:27:31 +08:00
