Fangjun Kuang
6122a678f5
Refactor exporting NeMo models ( #2362 )
...
Refactors and extends model export support to include new NeMo Parakeet TDT int8 variants for English and Japanese, updating the Kotlin API, export scripts, test runners, and CI workflows.
- Added support for two new int8 model types in OfflineRecognizer.kt.
- Enhanced Python export scripts to perform dynamic quantization and metadata injection.
- Updated shell scripts and GitHub workflows to package, test, and publish int8 model artifacts.
2025-07-09 16:02:12 +08:00
Fangjun Kuang
f1405779cf
Fix nemo feature normalization in test code ( #2361 )
2025-07-08 15:41:56 +08:00
Fangjun Kuang
0e738c356c
Add C++ runtime and Python API for NeMo Canary models ( #2352 )
2025-07-07 17:03:49 +08:00
Fangjun Kuang
fce481c125
Add meta data to NeMo canary ONNX models ( #2351 )
2025-07-07 00:12:20 +08:00
lucaelin
5ebb71909b
fix(canary): use dynamo export, single input_ids and avoid 0/1 specialization ( #2348 )
2025-07-06 18:24:06 +08:00
Fangjun Kuang
6cb44d44e9
Export nvidia/canary-180m-flash to sherpa-onnx ( #2272 )
2025-06-02 22:28:15 +08:00
Fangjun Kuang
8e6826521e
Update kaldi-native-fbank. ( #2259 )
...
Now it supports FFT of an even number, not necessarily a power of 2.
2025-05-29 10:34:22 +08:00
Fangjun Kuang
d660d5adea
export parakeet-tdt-0.6b-v2 to sherpa-onnx ( #2180 )
2025-05-06 16:32:59 +08:00
Fangjun Kuang
be0f382a54
Support Giga AM transducer V2 ( #2136 )
2025-04-20 10:15:20 +08:00
Roman Inflianskas
01110cc22b
Add support for GigaAM-CTC-v2 ( #2135 )
...
Related to #2098 .
2025-04-19 22:13:39 +08:00
Fangjun Kuang
707cf792c5
Add GigaAM NeMo transducer model for Russian ASR ( #1467 )
2024-10-25 15:20:13 +08:00
Fangjun Kuang
b41f6d2c94
Support GigaAM CTC models for Russian ASR ( #1464 )
...
See also https://github.com/salute-developers/GigaAM
2024-10-25 10:55:16 +08:00
Fangjun Kuang
df4150dc5d
Upload speaker embedding models to huggingface ( #1428 )
...
See also
https://huggingface.co/spaces/k2-fsa/speaker-diarization
2024-10-14 16:20:00 +08:00
Fangjun Kuang
11f0cb7e1c
Support Parakeet models from NeMo ( #1381 )
2024-09-27 17:12:00 +08:00
Fangjun Kuang
46e4e5b7ac
Add C++ support for streaming NeMo CTC models. ( #857 )
2024-05-10 16:26:43 +08:00
Fangjun Kuang
5ed3ec1c04
Export non-streaming NeMo faster conformer hybrid transducer and ctc to sherpa-onnx ( #847 )
2024-05-09 13:59:47 +08:00
Fangjun Kuang
68b25abf27
Export NeMo FastConformer Hybrid Transducer Large Streaming to ONNX ( #844 )
2024-05-08 19:07:49 +08:00
Fangjun Kuang
a9f936e92b
Export NeMo FastConformer Hybrid Transducer-CTC Large Streaming to ONNX. ( #843 )
2024-05-08 12:33:46 +08:00
Fangjun Kuang
68a525a024
Export speaker verification models from NeMo to ONNX ( #526 )
2024-01-13 19:49:45 +08:00
