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
Fangjun Kuang
26d5f1fa01
Fix kokoro lexicon. ( #1886 )
...
还钱 is mispronounced.
2025-02-18 11:09:16 +08:00
Fangjun Kuang
87a968b55d
Add Go API for FireRedAsr AED Model ( #1879 )
2025-02-17 16:04:07 +08:00
Fangjun Kuang
d95d43112d
Add C# API for FireRedAsr Model ( #1875 )
2025-02-17 13:32:41 +08:00
ilibx
2dd84b4582
[update] fixed bug: create golang instance succeed while the c struct create failed ( #1860 )
2025-02-14 14:20:29 +08:00
Fangjun Kuang
8b8ef1090b
Fix CI ( #1841 )
2025-02-11 12:27:09 +08:00
Fangjun Kuang
f5bf8c8d4a
Add Go API for audio tagging ( #1840 )
2025-02-11 12:07:28 +08:00
Fangjun Kuang
d5da9430e8
Add PengChengStarling models to sherpa-onnx ( #1835 )
2025-02-10 18:23:40 +08:00
Fangjun Kuang
9559a10bd3
Add C++ support for MatchaTTS models not from icefall. ( #1834 )
2025-02-10 15:38:29 +08:00
Fangjun Kuang
7d62ccf1fe
Export MatchaTTS fa-en model to sherpa-onnx ( #1832 )
2025-02-10 14:38:08 +08:00
Fangjun Kuang
69f489f0cd
Support scaling the duration of a pause in TTS. ( #1820 )
2025-02-08 12:47:26 +08:00
Fangjun Kuang
ae32dfaa56
Add C# API for Kokoro TTS 1.0 ( #1805 )
2025-02-07 15:39:03 +08:00
Fangjun Kuang
e1a88a799f
Add Go API for Kokoro TTS 1.0 ( #1804 )
2025-02-07 15:18:02 +08:00
Fangjun Kuang
a52b819fb5
Add Android demo for Kokoro TTS 1.0 ( #1799 )
2025-02-07 13:07:30 +08:00
Fangjun Kuang
4372a7a7b0
Add Java and Koltin API for Kokoro TTS 1.0 ( #1798 )
2025-02-07 09:59:27 +08:00
Fangjun Kuang
c84a833863
Add C++ and Python API for Kokoro 1.0 multilingual TTS model ( #1795 )
2025-02-06 22:57:13 +08:00
Fangjun Kuang
08cefe8488
Export Kokoro 1.0 to sherpa-onnx ( #1788 )
2025-02-05 08:24:43 +08:00
Fangjun Kuang
8b989a851c
Fix keyword spotting. ( #1689 )
...
Reset the stream right after detecting a keyword
2025-01-20 16:41:10 +08:00
Fangjun Kuang
99cef4198b
Add Koltin and Java API for Kokoro TTS models ( #1728 )
2025-01-17 17:36:13 +08:00
Fangjun Kuang
2086f8c55b
Add Go API for Kokoro TTS models ( #1722 )
2025-01-16 17:35:31 +08:00
Fangjun Kuang
cc812e6237
Add C# API for Kokoro TTS models ( #1720 )
2025-01-16 16:30:10 +08:00
Fangjun Kuang
9efe26a646
Export kokoro to sherpa-onnx ( #1713 )
2025-01-15 16:49:10 +08:00
Fangjun Kuang
0d20558b5e
Fix passing strings from C# to C. ( #1701 )
...
See also
https://github.com/k2-fsa/sherpa-onnx/issues/1695#issuecomment-2585725190
We need to place a 0 at the end of the buffer.
2025-01-13 10:17:04 +08:00
徐络溟
ecc653871d
Fix: export-onnx.py(expected all tensors to be on the same device) ( #1699 )
...
由于SenseVoiceSmall.from_pretrained()
调用的funasr.auto.auto_model.AutoModel.build_model()默认device是cuda
(在cuda available的环境中)
```py
device = kwargs.get("device", "cuda")
if not torch.cuda.is_available() or kwargs.get("ngpu", 1) == 0:
device = "cpu"
kwargs["batch_size"] = 1
kwargs["device"] = device
```
而export-onnx.py里的tensor默认都是cpu, 导致
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu
所以直接在加载model的时候指定cpu
2025-01-10 19:26:36 +08:00
Fangjun Kuang
46330b25cc
Add Go API for MatchaTTS models ( #1685 )
2025-01-06 08:03:03 +08:00
Fangjun Kuang
1fe5fe495f
Add Android demo for MatchaTTS models. ( #1683 )
2025-01-06 06:44:09 +08:00
Fangjun Kuang
3eced3e7ee
Add C# and JavaScript (wasm) API for MatchaTTS models ( #1682 )
2025-01-05 15:08:19 +08:00
Fangjun Kuang
0e299f30f5
Add JavaScript API (node-addon-api) for MatchaTTS models. ( #1677 )
2025-01-03 15:14:28 +08:00
Fangjun Kuang
49154c957b
Add Go API for Keyword spotting ( #1662 )
2024-12-31 11:25:32 +08:00
Fangjun Kuang
08d771337b
Add a byte-level BPE Chinese+English non-streaming zipformer model ( #1645 )
2024-12-24 16:56:49 +08:00
Fangjun Kuang
fe3265aa25
Add new tts models for Latvia and Persian+English ( #1644 )
2024-12-24 15:16:02 +08:00
Fangjun Kuang
b76cd9033a
Support decoding with byte-level BPE (bbpe) models. ( #1633 )
2024-12-20 19:21:32 +08:00
Fangjun Kuang
1bae4085ca
Add speaker diarization API for HarmonyOS. ( #1609 )
2024-12-10 16:03:03 +08:00
Fangjun Kuang
84821b1f99
Fix building node-addon package ( #1598 )
2024-12-06 10:11:18 +08:00
Fangjun Kuang
dc3287f3a8
Add HarmonyOS support for text-to-speech. ( #1584 )
2024-12-01 21:43:34 +08:00
Fangjun Kuang
c9d3b6cd8c
Add microphone demo about VAD+ASR for HarmonyOS ( #1581 )
2024-11-30 15:23:45 +08:00
Fangjun Kuang
299f2392e2
Add CI to build HAPs for HarmonyOS ( #1578 )
2024-11-29 21:13:01 +08:00
Fangjun Kuang
315d8e2a47
Publish sherpa_onnx.har for HarmonyOS ( #1572 )
2024-11-28 17:30:16 +08:00
Fangjun Kuang
c34ab35591
Add Android APK for streaming Paraformer ASR ( #1538 )
2024-11-14 20:57:35 +08:00
Fangjun Kuang
8436ba834c
Add WebAssembly example for VAD + Moonshine models. ( #1535 )
2024-11-13 21:06:50 +08:00
Fangjun Kuang
a16c9aff8b
Add Lazarus example for Moonshine models. ( #1532 )
2024-11-13 00:04:16 +08:00
Fangjun Kuang
4eeb336f59
Export the English TTS model from MeloTTS ( #1509 )
2024-11-04 07:54:19 +08:00
Fangjun Kuang
a3c89aa0d8
Add two-pass ASR Android APKs for Moonshine models. ( #1499 )
2024-10-31 17:54:16 +08:00
Fangjun Kuang
3622104133
Add C# API for Moonshine models. ( #1483 )
...
* Also, return timestamps for non-streaming ASR.
2024-10-27 13:14:25 +08:00
Fangjun Kuang
6f261d39f3
Add JavaScript API for Moonshine models ( #1480 )
2024-10-27 11:31:01 +08:00
Fangjun Kuang
3d3edabb5f
Add Go API for Moonshine models ( #1479 )
2024-10-27 09:39:09 +08:00
Fangjun Kuang
052b8645ba
Add Go API examples for adding punctuations to text. ( #1478 )
2024-10-27 09:04:05 +08:00
