From c759fef0aacefdcb89daa37f8ed39e471fd91e9a Mon Sep 17 00:00:00 2001 From: huangyuxin Date: Mon, 13 Dec 2021 06:38:16 +0000 Subject: [PATCH 01/23] move pypi-kenlm from install requirements to develop requirements --- setup.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/setup.py b/setup.py index 1ac671f1c..a5b773edf 100644 --- a/setup.py +++ b/setup.py @@ -46,7 +46,6 @@ requirements = { "paddleaudio", "paddlespeech_feat", "praatio~=4.1", - "pypi-kenlm", "pypinyin", "python-dateutil", "pyworld", @@ -71,6 +70,7 @@ requirements = { "phkit", "Pillow", "pybind11", + "pypi-kenlm", "snakeviz", "sox", "soxbindings", From 9e31a606d10a3b34e8b236637f01b3257e786ed0 Mon Sep 17 00:00:00 2001 From: Jackwaterveg <87408988+Jackwaterveg@users.noreply.github.com> Date: Mon, 13 Dec 2021 14:46:20 +0800 Subject: [PATCH 02/23] set default encoding utf8 for win (#1101) Co-authored-by: KP <109694228@qq.com> --- paddlespeech/cli/__init__.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/paddlespeech/cli/__init__.py b/paddlespeech/cli/__init__.py index 99a53c37e..c82168aee 100644 --- a/paddlespeech/cli/__init__.py +++ b/paddlespeech/cli/__init__.py @@ -11,9 +11,13 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. + +import _locale from .asr import ASRExecutor from .base_commands import BaseCommand from .base_commands import HelpCommand from .cls import CLSExecutor from .st import STExecutor from .tts import TTSExecutor + +_locale._getdefaultlocale = (lambda *args: ['en_US', 'utf8']) From 7acf62d208b0092b5fb4163fdd6497409b1cc063 Mon Sep 17 00:00:00 2001 From: Hui Zhang Date: Mon, 13 Dec 2021 15:25:40 +0800 Subject: [PATCH 03/23] fix release model (#1106) --- docs/source/released_model.md | 48 ++++++++++++++++++----------------- 1 file changed, 25 insertions(+), 23 deletions(-) diff --git a/docs/source/released_model.md b/docs/source/released_model.md index 58650e593..1b61ccc7b 100644 --- a/docs/source/released_model.md +++ b/docs/source/released_model.md @@ -2,32 +2,31 @@ ## Speech-to-Text Models -### Acoustic Model Released in paddle 2.X -Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER | Hours of speech | example link +### Speech Recognition Model +Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER | Hours of speech | Example Link :-------------:| :------------:| :-----: | -----: | :----------------- |:--------- | :---------- | :--------- | :----------- -[Ds2 Online Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/aishell_ds2_online_cer8.00_release.tar.gz) | Aishell Dataset | Char-based | 345 MB | 2 Conv + 5 LSTM layers with only forward direction | 0.080 |-| 151 h | [D2 Online Aishell S0 Example](../../examples/aishell/asr0) -[Ds2 Offline Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/ds2.model.tar.gz)| Aishell Dataset | Char-based | 306 MB | 2 Conv + 3 bidirectional GRU layers| 0.064 |-| 151 h | [Ds2 Offline Aishell S0 Example](../../examples/aishell/asr0) -[Conformer Online Aishell ASR1 Model](https://deepspeech.bj.bcebos.com/release2.1/aishell/s1/aishell.chunk.release.tar.gz) | Aishell Dataset | Char-based | 283 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0594 |-| 151 h | [Conformer Online Aishell S1 Example](../../examples/aishell/s1) -[Conformer Offline Aishell ASR1 Model](https://deepspeech.bj.bcebos.com/release2.1/aishell/s1/aishell.release.tar.gz) | Aishell Dataset | Char-based | 284 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0547 |-| 151 h | [Conformer Offline Aishell S1 Example](../../examples/aishell/s1) -[Conformer Librispeech ASR1 Model](https://deepspeech.bj.bcebos.com/release2.1/librispeech/s1/conformer.release.tar.gz) | Librispeech Dataset | subword-based | 287 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring |-| 0.0325 | 960 h | [Conformer Librispeech S1 example](../../example/librispeech/s1) -[Transformer Librispeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr1/transformer.model.tar.gz) | Librispeech Dataset | subword-based | 131 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: Attention rescoring |-| 0.0410 | 960 h | [Transformer Librispeech S1 example](../../example/librispeech/s1) -[Transformer Librispeech ASR2 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr2/transformer.model.tar.gz) | Librispeech Dataset | subword-based | 131 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: JoinCTC w/ LM |-| 0.024 | 960 h | [Transformer Librispeech S2 example](../../example/librispeech/s2) - - -### Acoustic Model Transformed from paddle 1.8 -Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER | Hours of speech -:-------------:| :------------:| :-----: | -----: | :----------------- | :---------- | :---------- | :--------- -[Ds2 Offline Aishell model](https://deepspeech.bj.bcebos.com/mandarin_models/aishell_model_v1.8_to_v2.x.tar.gz)|Aishell Dataset| Char-based| 234 MB| 2 Conv + 3 bidirectional GRU layers| 0.0804 |-| 151 h| -[Ds2 Offline Librispeech model](https://deepspeech.bj.bcebos.com/eng_models/librispeech_v1.8_to_v2.x.tar.gz)|Librispeech Dataset| Word-based| 307 MB| 2 Conv + 3 bidirectional sharing weight RNN layers |-| 0.0685| 960 h| -[Ds2 Offline Baidu en8k model](https://deepspeech.bj.bcebos.com/eng_models/baidu_en8k_v1.8_to_v2.x.tar.gz)|Baidu Internal English Dataset| Word-based| 273 MB| 2 Conv + 3 bidirectional GRU layers |-| 0.0541 | 8628 h| - -### Language Model Released +[Ds2 Online Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/aishell_ds2_online_cer8.00_release.tar.gz) | Aishell Dataset | Char-based | 345 MB | 2 Conv + 5 LSTM layers with only forward direction | 0.080 |-| 151 h | [D2 Online Aishell ASR0](../../examples/aishell/asr0) +[Ds2 Offline Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/ds2.model.tar.gz)| Aishell Dataset | Char-based | 306 MB | 2 Conv + 3 bidirectional GRU layers| 0.064 |-| 151 h | [Ds2 Offline Aishell ASR0](../../examples/aishell/asr0) +[Conformer Online Aishell ASR1 Model](https://deepspeech.bj.bcebos.com/release2.1/aishell/s1/aishell.chunk.release.tar.gz) | Aishell Dataset | Char-based | 283 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0594 |-| 151 h | [Conformer Online Aishell ASR1](../../examples/aishell/asr1) +[Conformer Offline Aishell ASR1 Model](https://deepspeech.bj.bcebos.com/release2.1/aishell/s1/aishell.release.tar.gz) | Aishell Dataset | Char-based | 284 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0547 |-| 151 h | [Conformer Offline Aishell ASR1](../../examples/aishell/asr1) +[Transformer Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/transformer.model.tar.gz) | Aishell Dataset | Char-based | 128 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0538 || 151 h | [Transformer Aishell ASR1](../../examples/aishell/asr1) +[Conformer Librispeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr1/conformer.model.tar.gz) | Librispeech Dataset | subword-based | 191 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring |-| 0.0337 | 960 h | [Conformer Librispeech ASR1](../../example/librispeech/asr1) +[Transformer Librispeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr1/transformer.model.tar.gz) | Librispeech Dataset | subword-based | 131 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: Attention rescoring |-| 0.0381 | 960 h | [Transformer Librispeech ASR1](../../example/librispeech/asr1) +[Transformer Librispeech ASR2 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr2/transformer.model.tar.gz) | Librispeech Dataset | subword-based | 131 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: JoinCTC w/ LM |-| 0.0240 | 960 h | [Transformer Librispeech ASR2](../../example/librispeech/asr2) + +### Language Model based on NGram Language Model | Training Data | Token-based | Size | Descriptions :-------------:| :------------:| :-----: | -----: | :----------------- [English LM](https://deepspeech.bj.bcebos.com/en_lm/common_crawl_00.prune01111.trie.klm) | [CommonCrawl(en.00)](http://web-language-models.s3-website-us-east-1.amazonaws.com/ngrams/en/deduped/en.00.deduped.xz) | Word-based | 8.3 GB | Pruned with 0 1 1 1 1;
About 1.85 billion n-grams;
'trie' binary with '-a 22 -q 8 -b 8' [Mandarin LM Small](https://deepspeech.bj.bcebos.com/zh_lm/zh_giga.no_cna_cmn.prune01244.klm) | Baidu Internal Corpus | Char-based | 2.8 GB | Pruned with 0 1 2 4 4;
About 0.13 billion n-grams;
'probing' binary with default settings [Mandarin LM Large](https://deepspeech.bj.bcebos.com/zh_lm/zhidao_giga.klm) | Baidu Internal Corpus | Char-based | 70.4 GB | No Pruning;
About 3.7 billion n-grams;
'probing' binary with default settings +### Speech Translation Models + +| Model | Training Data | Token-based | Size | Descriptions | BLEU | Example Link | +| ------------------------------------------------------------ | ------------- | ----------- | ---- | ------------------------------------------------------------ | ----- | ------------------------------------------------------------ | +| [Transformer FAT-ST MTL En-Zh](https://paddlespeech.bj.bcebos.com/s2t/ted_en_zh/st1/fat_st_ted-en-zh.tar.gz) | Ted-En-Zh | Spm | | Encoder:Transformer, Decoder:Transformer,
Decoding method: Attention | 20.80 | [Transformer Ted-En-Zh ST1](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/examples/ted_en_zh/st1) | + ## Text-to-Speech Models @@ -69,8 +68,11 @@ PANN | Audioset| [audioset_tagging_cnn](https://github.com/qiuqiangkong/audioset PANN | ESC-50 |[pann-esc50]("./examples/esc50/cls0")|[panns_cnn6.tar.gz](https://paddlespeech.bj.bcebos.com/cls/panns_cnn6.tar.gz), [panns_cnn10](https://paddlespeech.bj.bcebos.com/cls/panns_cnn10.tar.gz), [panns_cnn14.tar.gz](https://paddlespeech.bj.bcebos.com/cls/panns_cnn14.tar.gz) -## Speech Translation Models +## Speech Recognition Model from paddle 1.8 + +| Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER | Hours of speech | +| :----------------------------------------------------------: | :----------------------------: | :---------: | -----: | :------------------------------------------------- | :----- | :----- | :-------------- | +| [Ds2 Offline Aishell model](https://deepspeech.bj.bcebos.com/mandarin_models/aishell_model_v1.8_to_v2.x.tar.gz) | Aishell Dataset | Char-based | 234 MB | 2 Conv + 3 bidirectional GRU layers | 0.0804 | - | 151 h | +| [Ds2 Offline Librispeech model](https://deepspeech.bj.bcebos.com/eng_models/librispeech_v1.8_to_v2.x.tar.gz) | Librispeech Dataset | Word-based | 307 MB | 2 Conv + 3 bidirectional sharing weight RNN layers | - | 0.0685 | 960 h | +| [Ds2 Offline Baidu en8k model](https://deepspeech.bj.bcebos.com/eng_models/baidu_en8k_v1.8_to_v2.x.tar.gz) | Baidu Internal English Dataset | Word-based | 273 MB | 2 Conv + 3 bidirectional GRU layers | - | 0.0541 | 8628 h | -Model Type | Dataset| Example Link | Pretrained Models | Model Size -:-------------:| :------------:| :-----: | :-----: | :-----: -FAT-ST | TED En-Zh |[FAT + Transformer+ASR MTL](./examples/ted_en_zh/st1)|[fat_st_ted-en-zh.tar.gz](https://paddlespeech.bj.bcebos.com/s2t/ted_en_zh/st1/fat_st_ted-en-zh.tar.gz) | 50.26M From c30549f0a7865a6f459361be38638a8eec34173a Mon Sep 17 00:00:00 2001 From: TianYuan Date: Mon, 13 Dec 2021 16:02:21 +0800 Subject: [PATCH 04/23] Update README.md --- README.md | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/README.md b/README.md index ca0e0b461..7ccbe4c5c 100644 --- a/README.md +++ b/README.md @@ -221,15 +221,15 @@ The current hyperlinks redirect to [Previous Parakeet](https://github.com/Paddle - - - - + + + + - +
Text-to-Speech Module Type Model Type Dataset Link Text-to-Speech Module Type Model Type Dataset Link
Text Frontend Text Frontend   tn / g2p @@ -315,10 +315,10 @@ The current hyperlinks redirect to [Previous Parakeet](https://github.com/Paddle - - - - + + + + From 2a1cbf2d85e4f517aae2b8b7ea8ff080bdcbbef2 Mon Sep 17 00:00:00 2001 From: TianYuan Date: Mon, 13 Dec 2021 16:45:41 +0800 Subject: [PATCH 05/23] Update README.md --- demos/speech_translation/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/demos/speech_translation/README.md b/demos/speech_translation/README.md index 8bb322c52..caca05dd1 100644 --- a/demos/speech_translation/README.md +++ b/demos/speech_translation/README.md @@ -19,7 +19,7 @@ Here are sample files for this demo that can be downloaded: wget https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav ``` -### 3. Usage +### 3. Usage (not support for Windows now) - Command Line(Recommended) ```bash paddlespeech st --input ./en.wav From 7883e2c22ec1c8a1aa089fcbdaecacab1000282b Mon Sep 17 00:00:00 2001 From: TianYuan Date: Mon, 13 Dec 2021 16:47:24 +0800 Subject: [PATCH 06/23] Update README.md --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 7ccbe4c5c..1c94914fa 100644 --- a/README.md +++ b/README.md @@ -139,6 +139,7 @@ paddlespeech cls --input input.wav paddlespeech asr --lang zh --input input_16k.wav ``` **Speech Translation** (English to Chinese) + (not support for Windows now) ```shell paddlespeech st --input input_16k.wav ``` From 965a57ef0e8db2411708db1292f497e7461f5a6d Mon Sep 17 00:00:00 2001 From: TianYuan Date: Mon, 13 Dec 2021 16:48:24 +0800 Subject: [PATCH 07/23] Update README.md --- paddlespeech/cli/README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/paddlespeech/cli/README.md b/paddlespeech/cli/README.md index 25f1f718b..34466ec2f 100644 --- a/paddlespeech/cli/README.md +++ b/paddlespeech/cli/README.md @@ -17,6 +17,8 @@ ``` ## Speech Translation (English to Chinese) + + (not support for Windows now) ```bash paddlespeech st --input input_16k.wav ``` From e98e80e82ab94ba4a89b141dd7078e42679fdf59 Mon Sep 17 00:00:00 2001 From: TianYuan Date: Mon, 13 Dec 2021 16:49:23 +0800 Subject: [PATCH 08/23] Update README.md --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 1c94914fa..a1d6777e1 100644 --- a/README.md +++ b/README.md @@ -139,7 +139,8 @@ paddlespeech cls --input input.wav paddlespeech asr --lang zh --input input_16k.wav ``` **Speech Translation** (English to Chinese) - (not support for Windows now) + +(not support for Windows now) ```shell paddlespeech st --input input_16k.wav ``` From ca12a83d5a8a228e7bf04b0928a30cc61df870a0 Mon Sep 17 00:00:00 2001 From: TianYuan Date: Mon, 13 Dec 2021 11:36:28 +0000 Subject: [PATCH 09/23] update voc name --- paddlespeech/cli/tts/infer.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/paddlespeech/cli/tts/infer.py b/paddlespeech/cli/tts/infer.py index 771b7d6dc..2684e9edf 100644 --- a/paddlespeech/cli/tts/infer.py +++ b/paddlespeech/cli/tts/infer.py @@ -465,7 +465,7 @@ class TTSExecutor(BaseExecutor): # vocoder # model: {model_name}_{dataset} - voc_name = '_'.join(voc.split('_')[:-1]) + voc_name = voc[:voc.rindex('_')] voc_class = dynamic_import(voc_name, model_alias) voc_inference_class = dynamic_import(voc_name + '_inference', model_alias) From 84025c5ffef97080b8012be9c0f190b91ed3281f Mon Sep 17 00:00:00 2001 From: TianYuan Date: Mon, 13 Dec 2021 19:46:05 +0800 Subject: [PATCH 10/23] Rename READEME.md to README.md --- examples/aishell/asr1/{READEME.md => README.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename examples/aishell/asr1/{READEME.md => README.md} (100%) diff --git a/examples/aishell/asr1/READEME.md b/examples/aishell/asr1/README.md similarity index 100% rename from examples/aishell/asr1/READEME.md rename to examples/aishell/asr1/README.md From 9db1710ba78c18185e5180f366ff8e5e3d70b5e2 Mon Sep 17 00:00:00 2001 From: TianYuan Date: Mon, 13 Dec 2021 20:08:43 +0800 Subject: [PATCH 11/23] add conformer demos (#1108) --- docs/source/tts/demo.rst | 101 +++++++++++++++++++++++ paddlespeech/t2s/frontend/zh_frontend.py | 4 + 2 files changed, 105 insertions(+) diff --git a/docs/source/tts/demo.rst b/docs/source/tts/demo.rst index 4c2f86b14..ca2fd98e4 100644 --- a/docs/source/tts/demo.rst +++ b/docs/source/tts/demo.rst @@ -455,6 +455,7 @@ Audio samples generated by a TTS system. Text is first transformed into spectrog CSMSC(Chinese)

+
Task Dataset Model Type Link Task Dataset Model Type Link
@@ -634,6 +635,106 @@ Audio samples generated by a TTS system. Text is first transformed into spectrog
Text
+ +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
FastSpeech2-Conformer + ParallelWaveGAN
+ +
+ +
+ +
+ +
+ +
+ +
+ +
+ +
+ +


diff --git a/paddlespeech/t2s/frontend/zh_frontend.py b/paddlespeech/t2s/frontend/zh_frontend.py index b59060a36..8eb55ff25 100644 --- a/paddlespeech/t2s/frontend/zh_frontend.py +++ b/paddlespeech/t2s/frontend/zh_frontend.py @@ -137,6 +137,10 @@ class Frontend(): phones_list.append(phones) if merge_sentences: merge_list = sum(phones_list, []) + # rm the last 'sp' to avoid the noise at the end + # cause in the training data, no 'sp' in the end + if merge_list[-1] == 'sp': + merge_list = merge_list[:-1] phones_list = [] phones_list.append(merge_list) return phones_list From cce45cbcdaf5fbd1dee1b7c1b9880a5d1fdf618d Mon Sep 17 00:00:00 2001 From: AK391 <81195143+AK391@users.noreply.github.com> Date: Mon, 13 Dec 2021 18:20:22 -0500 Subject: [PATCH 12/23] add HF badge --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index a1d6777e1..b071ed803 100644 --- a/README.md +++ b/README.md @@ -149,6 +149,8 @@ paddlespeech st --input input_16k.wav paddlespeech tts --input "你好，欢迎使用百度飞桨深度学习框架！" --output output.wav ``` +- web demo for Text to Speech is integrated to [Huggingface Spaces](https://huggingface.co/spaces) with [Gradio](https://github.com/gradio-app/gradio). See demo: [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/akhaliq/paddlespeech) + If you want to try more functions like training and tuning, please have a look at [Speech-to-Text Quick Start](./docs/source/asr/quick_start.md) and [Text-to-Speech Quick Start](./docs/source/tts/quick_start.md). ## Model List From 3de4130dfcb02d6dfd0af6234991532405679bb0 Mon Sep 17 00:00:00 2001 From: TianYuan Date: Tue, 14 Dec 2021 02:34:44 +0000 Subject: [PATCH 13/23] update am name --- paddlespeech/cli/tts/infer.py | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/paddlespeech/cli/tts/infer.py b/paddlespeech/cli/tts/infer.py index 2684e9edf..65d6d5282 100644 --- a/paddlespeech/cli/tts/infer.py +++ b/paddlespeech/cli/tts/infer.py @@ -403,8 +403,6 @@ class TTSExecutor(BaseExecutor): with open(self.voc_config) as f: self.voc_config = CfgNode(yaml.safe_load(f)) - # Enter the path of model root - with open(self.phones_dict, "r") as f: phn_id = [line.strip().split() for line in f.readlines()] vocab_size = len(phn_id) @@ -499,10 +497,10 @@ class TTSExecutor(BaseExecutor): """ Model inference and result stored in self.output. """ - model_name = am[:am.rindex('_')] - dataset = am[am.rindex('_') + 1:] + am_name = am[:am.rindex('_')] + am_dataset = am[am.rindex('_') + 1:] get_tone_ids = False - if 'speedyspeech' in model_name: + if am_name == 'speedyspeech': get_tone_ids = True if lang == 'zh': input_ids = self.frontend.get_input_ids( @@ -519,15 +517,14 @@ class TTSExecutor(BaseExecutor): print("lang should in {'zh', 'en'}!") # am - if 'speedyspeech' in model_name: + if am_name == 'speedyspeech': mel = self.am_inference(phone_ids, tone_ids) # fastspeech2 else: # multi speaker - if dataset in {"aishell3", "vctk"}: + if am_dataset in {"aishell3", "vctk"}: mel = self.am_inference( phone_ids, spk_id=paddle.to_tensor(spk_id)) - else: mel = self.am_inference(phone_ids) From 9986b435c1b6d192285013e4bb0e4a390ad56297 Mon Sep 17 00:00:00 2001 From: AK391 <81195143+AK391@users.noreply.github.com> Date: Mon, 13 Dec 2021 21:57:09 -0500 Subject: [PATCH 14/23] move badge --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index b071ed803..f8b17c578 100644 --- a/README.md +++ b/README.md @@ -14,6 +14,7 @@ ![License](https://img.shields.io/badge/license-Apache%202-red.svg) ![python version](https://img.shields.io/badge/python-3.7+-orange.svg) ![support os](https://img.shields.io/badge/os-linux-yellow.svg) +[![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/akhaliq/paddlespeech)