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
3bf986d08d
Support non-streaming zipformer CTC ASR models ( #2340 )
...
This PR adds support for non-streaming Zipformer CTC ASR models across
multiple language bindings, WebAssembly, examples, and CI workflows.
- Introduces a new OfflineZipformerCtcModelConfig in C/C++, Python, Swift, Java, Kotlin, Go, Dart, Pascal, and C# APIs
- Updates initialization, freeing, and recognition logic to include Zipformer CTC in WASM and Node.js
- Adds example scripts and CI steps for downloading, building, and running Zipformer CTC models
Model doc is available at
https://k2-fsa.github.io/sherpa/onnx/pretrained_models/offline-ctc/icefall/zipformer.html
2025-07-04 15:57:07 +08:00
Fangjun Kuang
9fe25cc06f
Fix VAD+ASR C++ example. ( #2335 )
...
It was not able to handle short audios., e.g., 2.1 seconds.
2025-07-02 15:52:49 +08:00
Fangjun Kuang
046ce01203
Add TTS engline APKs for more models ( #2327 )
2025-06-30 13:36:29 +08:00
Fangjun Kuang
bda427f4b2
Add API to get version information ( #2309 )
2025-06-25 00:22:21 +08:00
Fangjun Kuang
6982b86c66
Support extra languages in multi-lang kokoro tts ( #2303 )
2025-06-20 11:22:52 +08:00
Fangjun Kuang
a6095f5f64
Fix building for Pascal ( #2305 )
2025-06-20 11:10:07 +08:00
Fangjun Kuang
59d118c256
Refactor kokoro export ( #2302 )
...
- generate samples for https://k2-fsa.github.io/sherpa/onnx/tts/all/
- provide int8 model for kokoro v0.19 kokoro-int8-en-v0_19.tar.bz2
2025-06-18 20:30:10 +08:00
Fangjun Kuang
2913cce77c
Add scripts for exporting Piper TTS models to sherpa-onnx ( #2299 )
2025-06-17 14:23:39 +08:00
Fangjun Kuang
4ae9382bae
Update TTS Engine APK to support multi-lang ( #2294 )
2025-06-17 14:16:48 +08:00
Fangjun Kuang
db632dacf3
Fix CI for windows ( #2279 )
2025-06-04 10:35:48 +08:00
Fangjun Kuang
6cb44d44e9
Export nvidia/canary-180m-flash to sherpa-onnx ( #2272 )
2025-06-02 22:28:15 +08:00
Fangjun Kuang
921f0f40cb
Add UVR models for source separation. ( #2266 )
2025-05-31 13:31:31 +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
16a3449945
Build APK with replace.fst ( #2254 )
2025-05-28 12:19:29 +08:00
Fangjun Kuang
716ba8317b
Add C++ runtime for spleeter about source separation ( #2242 )
2025-05-23 22:30:57 +08:00
Fangjun Kuang
55a44793e6
Export spleeter model to onnx for source separation ( #2237 )
2025-05-22 15:09:38 +08:00
Fangjun Kuang
d8bb20710d
Add script to build APK for simulated-streaming-asr. ( #2220 )
2025-05-15 15:40:22 +08:00
愚者自愚
116977b5d4
Add Go implementation of the TTS generation callback ( #2213 )
2025-05-14 16:09:31 +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
fcb4c4eb2c
Add Go API for homophone replacer ( #2168 )
2025-04-30 23:47:38 +08:00
Fangjun Kuang
50b5329572
Add C# API for homophone replacer ( #2165 )
2025-04-29 21:36:38 +08:00
Fangjun Kuang
7cbb1bc433
Upload more onnx ASR models ( #2141 )
2025-04-21 18:57:41 +08:00
Fangjun Kuang
6cabaa11bf
Export kokoro 1.0 int8 models ( #2137 )
2025-04-20 14:35:02 +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
639ad1744f
Add Javascript (WebAssembly) API for Dolphin CTC models ( #2093 )
2025-04-03 15:02:06 +08:00
Fangjun Kuang
ba7d8b63f0
Add Go API for Dolphin CTC models ( #2090 )
2025-04-03 00:02:09 +08:00
Fangjun Kuang
2dc0f91904
Add C# API for Dolphin CTC models ( #2089 )
2025-04-02 23:36:22 +08:00
Fangjun Kuang
da4aad1189
Add C and CXX API for Dolphin CTC models ( #2088 )
2025-04-02 21:54:20 +08:00
Fangjun Kuang
eee5575836
Add Kotlin and Java API for Dolphin CTC models ( #2086 )
2025-04-02 21:16:14 +08:00
Fangjun Kuang
8e51a97550
Add C++ runtime for silero_vad with RKNN ( #2078 )
2025-04-01 15:56:56 +08:00
Fangjun Kuang
3420c89883
Export silero_vad v4 to RKNN ( #2067 )
2025-03-30 12:00:52 +08:00
Fangjun Kuang
0aacf02dd8
Add C++ runtime for vocos ( #2014 )
2025-03-17 17:05:15 +08:00
Fangjun Kuang
623cdc9eec
Export vocos to sherpa-onnx ( #2012 )
2025-03-17 09:19:50 +08:00
Fangjun Kuang
c972554ad1
Add JavaScript API (wasm) for speech enhancement GTCRN models ( #2007 )
2025-03-15 17:41:23 +08:00
Fangjun Kuang
6a97f8adcf
Add JavaScript (node-addon) API for speech enhancement GTCRN models ( #1996 )
2025-03-12 15:52:01 +08:00
Fangjun Kuang
fd78a482df
Add Dart API for speech enhancement GTCRN models ( #1993 )
2025-03-12 12:39:08 +08:00
Fangjun Kuang
d78f408362
Add Go API for speech enhancement GTCRN models ( #1991 )
2025-03-11 19:33:05 +08:00
Fangjun Kuang
d3e27d5e21
Add C# API for speech enhancement GTCRN models ( #1990 )
2025-03-11 18:58:17 +08:00
franck-li
8aaae91d4a
add SherpaOnnxOfflineRecognizerSetConfig binding for go, and optimize the new/free for C.struct_SherpaOnnxOfflineRecognizerConfig ptr ( #1976 )
...
Co-authored-by: liyuzhi <liyuzhi@info.easeus.com.cn >
2025-03-10 18:04:12 +08:00
Fangjun Kuang
6e261ed63f
Export gtcrn models to sherpa-onnx ( #1975 )
2025-03-10 11:31:18 +08:00
Fangjun Kuang
dfcbc8d40b
Add Kokoro v1.1-zh ( #1942 )
2025-02-28 15:47:59 +08:00
Fangjun Kuang
815ebac8f9
Fix building wheels for Python 3.7 ( #1933 )
2025-02-27 13:02:46 +08:00
xcel3011
b042f5e179
fix: AddPunct panic for Go( #1921 )
2025-02-25 18:09:28 +08:00
franck-li
0dcaf3a061
go.mod set to use go 1.17, and use unsafe.Slice to optimize the code ( #1920 )
...
Co-authored-by: liyuzhi <liyuzhi@info.easeus.com.cn >
2025-02-25 15:31:15 +08:00
franck-li
808587accd
change [1<<28] to [1<<10], to fix build issues on GOARCH=386 that [1<<28] too large ( #1916 )
...
Co-authored-by: liyuzhi <liyuzhi@info.easeus.com.cn >
2025-02-25 09:12:55 +08:00
Fangjun Kuang
4d79e6a007
Add C++ API for streaming zipformer ASR on RK NPU ( #1908 )
2025-02-24 19:07:37 +08:00
Sheldon Robinson
9c810ce3fe
Fix #1901 : UnicodeEncodeError running export_bpe_vocab.py ( #1902 )
2025-02-21 06:29:28 +08:00
Fangjun Kuang
774cf662a4
Fix generating Chinese lexicon for Kokoro TTS 1.0 ( #1888 )
2025-02-18 12:51:26 +08:00
