Cherry-pick to r1.4 branch #3798
Commits on Jun 11, 2024
-
-
[TTS] add opencpop PWGAN example (PaddlePaddle#3031)
* add opencpop voc, test=tts * soft link
-
-
[TTS] add opencpop HIFIGAN example (PaddlePaddle#3038)
* add opencpop voc, test=tts * soft link * add opencpop hifigan, test=tts * update
-
[ASR]add squeezeformer model (PaddlePaddle#2755)
* add squeezeformer model * change CodeStyle, test=asr * change CodeStyle, test=asr * fix subsample rate error, test=asr * merge classes as required, test=asr * change CodeStyle, test=asr * fix missing code, test=asr * split code to new file, test=asr * remove rel_shift, test=asr
-
-
-
-
-
-
-
[TTS]clean starganv2 vc model code and add docstring (PaddlePaddle#2987)
* clean code * add docstring
-
[Doc] change define asr server config to chunk asr config, test=doc (P…
…addlePaddle#3067) * Update README.md * Update README_cn.md
-
-
[TTS]fix elementwise_floordiv's fill_constant (PaddlePaddle#3075)
* fix elementwise_floordiv's fill_constant * add float converter for min_value in attention
-
-
-
-
-
[TTS]add starganv2 vc trainer (PaddlePaddle#3143)
* add starganv2 vc trainer * fix StarGANv2VCUpdater and losses * fix StarGANv2VCEvaluator * add some typehint
-
[TTS]【Hackathon + No.190】 + 模型复现：iSTFTNet (PaddlePaddle#3006)
* iSTFTNet implementation based on hifigan, not affect the function and execution of HIFIGAN * modify the comment in iSTFT.yaml * add the comments in hifigan * iSTFTNet implementation based on hifigan, not affect the function and execution of HIFIGAN * modify the comment in iSTFT.yaml * add the comments in hifigan * add iSTFTNet.md * modify the format of iSTFTNet.md * modify iSTFT.yaml and hifigan.py * Format code using pre-commit * modify hifigan.py,delete the unused self.istft_layer_id , move the self.output_conv behind else, change conv_post to output_conv * update iSTFTNet_csmsc_ckpt.zip download link * modify iSTFTNet.md * modify hifigan.py and iSTFT.yaml * modify iSTFTNet.md
-
add function for generating srt file (PaddlePaddle#3123)
* add function for generating srt file 在原来websocket_client.py的基础上，增加了由wav或mp3格式的音频文件生成对应srt格式字幕文件的功能 * add function for generating srt file 在原来websocket_client.py的基础上，增加了由wav或mp3格式的音频文件生成对应srt格式字幕文件的功能 * keep origin websocket_client.py 恢复原本的websocket_client.py文件 * add generating subtitle function into README * add generate subtitle funciton into README * add subtitle generation function * add subtitle generation function
-
-
-
-
-
-
-
-
-
-
-
-
-
[s2t] mv dataset into paddlespeech.dataset (PaddlePaddle#3183)
* mv dataset into paddlespeech.dataset * add aidatatang * fix import
-
-
[s2t] move s2t data preprocess into paddlespeech.dataset (PaddlePaddl…
…e#3189) * move s2t data preprocess into paddlespeech.dataset * avg model, compute wer, format rsl into paddlespeech.dataset * fix format rsl * fix avg ckpts
-
-
-
-
-
-
-
[s2t] fix cli args to config (PaddlePaddle#3194)
* fix cli args to config * fix train cli
-
-
[ASR] Support Hubert, fintuned on the librispeech dataset (PaddlePadd…
…le#3088) * librispeech hubert, test=asr * librispeech hubert, test=asr * hubert decode * review * copyright, notes, example related * hubert cli * pre-commit format * fix conflicts * fix conflicts * doc related * doc and train config * librispeech.py * support hubert cli
-
-
-
-
fix: 🐛 修复服务端 python ASREngine 无法使用conformer_talcs模型 (PaddlePaddle#3230)
* fix: 🐛 fix python ASREngine not pass codeswitch * docs: 📝 Update Docs * 修改模型判断方式
-
-
-
-
-
-
# 固话的正则 错误修改 参考https://github.com/speechio/chinese_text_normalization/blob/master/python/cn_tn.py 固化的正则为： pattern = re.compile(r"\D((0(10|2[1-3]|[3-9]\d{2})-?)?[1-9]\d{6,7})\D")
-
-
-
-
-
-
-
-
-
Final cleaning; Modified SSL/infer.py and README for wavlm inclusion …
…in model options
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Add XPU support for SpeedySpeech (PaddlePaddle#3502)
* Add XPU support for SpeedySpeech * fix typos * update description of nxpu
-
Add XPU support for FastSpeech2 (PaddlePaddle#3514)
* Add XPU support for FastSpeech2 * optimize
-
Update ge2e_clone.py (PaddlePaddle#3517)
修复在windows上的多空格错误
-
Fix Readme. (PaddlePaddle#3527)
* Update README.md * Update README_cn.md * Update README_cn.md * Update README.md
-
-
-
【benchmark】add max_mem_reserved for benchmark (PaddlePaddle#3604)
* fix profiler * add max_mem_reserved for benchmark
-
【benchmark】fix gpu_mem unit (PaddlePaddle#3634)
* fix profiler * add max_mem_reserved for benchmark * fix benchmark
-
Fixed PaddlePaddle#3605
-
bugfix: audio_len should be 1D, no 0D, which will raise list index out (
PaddlePaddle#3490) of range error in the following decode process Co-authored-by: Luzhenhui <[email protected]>
-
Update README.md (PaddlePaddle#3532)
Fixed a typo
-
fixed version for paddlepaddle. (PaddlePaddle#3701)
* fixed version for paddlepaddle. * fix code style
-
【Fix Speech Issue No.5】issue 3444 transformation import error (Paddle…
…Paddle#3779) * fix paddlespeech.s2t.transform.transformation import error * fix paddlespeech.s2t.transform import error
-
【Fix Speech Issue No.8】issue 3652 merge_yi function has a bug (Paddle…
…Paddle#3786) * 【Fix Speech Issue No.8】issue 3652 merge_yi function has a bug * 【Fix Speech Issue No.8】issue 3652 merge_yi function has a bug
-
【test】add cli test readme (PaddlePaddle#3784)
* add cli test readme * fix code style
-
【test】fix test cli bug (PaddlePaddle#3793)
* add cli test readme * fix code style * fix bug
-
-
adapt view behavior change, fix KeyError. (PaddlePaddle#3794)
* adapt view behavior change, fix KeyError. * fix readme demo run error. * fixed opencc version
