Merge branch 'develop' of github.com:iftaken/PaddleSpeech into dev-web-cmd

d5d94cbd · iftaken · a488ec83 · c6361a5f · d5d94cbd · a488ec83
52 changed file
--- a/docs/requirements.txt
+++ b/docs/requirements.txt
@@ -20,6 +20,7 @@ onnxruntime==1.10.0
 opencc
 paddlenlp
 paddlepaddle>=2.2.2
+paddlespeech_ctcdecoders
 paddlespeech_feat
 pandas
 pathos == 0.2.8
@@ -27,8 +28,8 @@ pattern_singleton
 Pillow>=9.0.0
 praatio==5.0.0
 prettytable
-pypinyin<=0.44.0
 pypinyin-dict
+pypinyin<=0.44.0
 python-dateutil
 pyworld==0.2.12
 recommonmark>=0.5.0

--- a/docs/source/api/paddlespeech.cls.exps.panns.deploy.predict.rst
+++ b/docs/source/api/paddlespeech.cls.exps.panns.deploy.predict.rst
-paddlespeech.cls.exps.panns.deploy.predict module
-=================================================
-
-.. automodule:: paddlespeech.cls.exps.panns.deploy.predict
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.cls.exps.panns.deploy.rst
+++ b/docs/source/api/paddlespeech.cls.exps.panns.deploy.rst
@@ -12,4 +12,3 @@ Submodules
 .. toctree::
   :maxdepth: 4

-   paddlespeech.cls.exps.panns.deploy.predict
--- a/docs/source/api/paddlespeech.cls.exps.panns.export_model.rst
+++ b/docs/source/api/paddlespeech.cls.exps.panns.export_model.rst
-paddlespeech.cls.exps.panns.export\_model module
-================================================
-
-.. automodule:: paddlespeech.cls.exps.panns.export_model
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.cls.exps.panns.predict.rst
+++ b/docs/source/api/paddlespeech.cls.exps.panns.predict.rst
-paddlespeech.cls.exps.panns.predict module
-==========================================
-
-.. automodule:: paddlespeech.cls.exps.panns.predict
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.cls.exps.panns.rst
+++ b/docs/source/api/paddlespeech.cls.exps.panns.rst
@@ -20,6 +20,3 @@ Submodules
 .. toctree::
   :maxdepth: 4

-   paddlespeech.cls.exps.panns.export_model
-   paddlespeech.cls.exps.panns.predict
-   paddlespeech.cls.exps.panns.train
--- a/docs/source/api/paddlespeech.cls.exps.panns.train.rst
+++ b/docs/source/api/paddlespeech.cls.exps.panns.train.rst
-paddlespeech.cls.exps.panns.train module
-========================================
-
-.. automodule:: paddlespeech.cls.exps.panns.train
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.kws.exps.mdtc.plot_det_curve.rst
+++ b/docs/source/api/paddlespeech.kws.exps.mdtc.plot_det_curve.rst
-paddlespeech.kws.exps.mdtc.plot\_det\_curve module
-==================================================
-
-.. automodule:: paddlespeech.kws.exps.mdtc.plot_det_curve
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.kws.exps.mdtc.rst
+++ b/docs/source/api/paddlespeech.kws.exps.mdtc.rst
@@ -14,6 +14,5 @@ Submodules

   paddlespeech.kws.exps.mdtc.collate
   paddlespeech.kws.exps.mdtc.compute_det
-   paddlespeech.kws.exps.mdtc.plot_det_curve
   paddlespeech.kws.exps.mdtc.score
   paddlespeech.kws.exps.mdtc.train
--- a/docs/source/api/paddlespeech.s2t.decoders.ctcdecoder.rst
+++ b/docs/source/api/paddlespeech.s2t.decoders.ctcdecoder.rst
@@ -13,5 +13,4 @@ Submodules
   :maxdepth: 4

   paddlespeech.s2t.decoders.ctcdecoder.decoders_deprecated
-   paddlespeech.s2t.decoders.ctcdecoder.scorer_deprecated
   paddlespeech.s2t.decoders.ctcdecoder.swig_wrapper
--- a/docs/source/api/paddlespeech.s2t.decoders.ctcdecoder.scorer_deprecated.rst
+++ b/docs/source/api/paddlespeech.s2t.decoders.ctcdecoder.scorer_deprecated.rst
-paddlespeech.s2t.decoders.ctcdecoder.scorer\_deprecated module
-==============================================================
-
-.. automodule:: paddlespeech.s2t.decoders.ctcdecoder.scorer_deprecated
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.decoders.recog_bin.rst
+++ b/docs/source/api/paddlespeech.s2t.decoders.recog_bin.rst
-paddlespeech.s2t.decoders.recog\_bin module
-===========================================
-
-.. automodule:: paddlespeech.s2t.decoders.recog_bin
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.decoders.rst
+++ b/docs/source/api/paddlespeech.s2t.decoders.rst
@@ -23,5 +23,4 @@ Submodules
   :maxdepth: 4

   paddlespeech.s2t.decoders.recog
-   paddlespeech.s2t.decoders.recog_bin
   paddlespeech.s2t.decoders.utils
--- a/docs/source/api/paddlespeech.s2t.decoders.scorers.ngram.rst
+++ b/docs/source/api/paddlespeech.s2t.decoders.scorers.ngram.rst
-paddlespeech.s2t.decoders.scorers.ngram module
-==============================================
-
-.. automodule:: paddlespeech.s2t.decoders.scorers.ngram
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.decoders.scorers.rst
+++ b/docs/source/api/paddlespeech.s2t.decoders.scorers.rst
@@ -15,5 +15,4 @@ Submodules
   paddlespeech.s2t.decoders.scorers.ctc
   paddlespeech.s2t.decoders.scorers.ctc_prefix_score
   paddlespeech.s2t.decoders.scorers.length_bonus
-   paddlespeech.s2t.decoders.scorers.ngram
   paddlespeech.s2t.decoders.scorers.scorer_interface
--- a/docs/source/api/paddlespeech.s2t.exps.deepspeech2.bin.deploy.client.rst
+++ b/docs/source/api/paddlespeech.s2t.exps.deepspeech2.bin.deploy.client.rst
-paddlespeech.s2t.exps.deepspeech2.bin.deploy.client module
-==========================================================
-
-.. automodule:: paddlespeech.s2t.exps.deepspeech2.bin.deploy.client
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.exps.deepspeech2.bin.deploy.record.rst
+++ b/docs/source/api/paddlespeech.s2t.exps.deepspeech2.bin.deploy.record.rst
-paddlespeech.s2t.exps.deepspeech2.bin.deploy.record module
-==========================================================
-
-.. automodule:: paddlespeech.s2t.exps.deepspeech2.bin.deploy.record
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.exps.deepspeech2.bin.deploy.rst
+++ b/docs/source/api/paddlespeech.s2t.exps.deepspeech2.bin.deploy.rst
@@ -12,8 +12,5 @@ Submodules
 .. toctree::
   :maxdepth: 4

-   paddlespeech.s2t.exps.deepspeech2.bin.deploy.client
-   paddlespeech.s2t.exps.deepspeech2.bin.deploy.record
   paddlespeech.s2t.exps.deepspeech2.bin.deploy.runtime
-   paddlespeech.s2t.exps.deepspeech2.bin.deploy.send
   paddlespeech.s2t.exps.deepspeech2.bin.deploy.server
--- a/docs/source/api/paddlespeech.s2t.exps.deepspeech2.bin.deploy.send.rst
+++ b/docs/source/api/paddlespeech.s2t.exps.deepspeech2.bin.deploy.send.rst
-paddlespeech.s2t.exps.deepspeech2.bin.deploy.send module
-========================================================
-
-.. automodule:: paddlespeech.s2t.exps.deepspeech2.bin.deploy.send
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.exps.u2.rst
+++ b/docs/source/api/paddlespeech.s2t.exps.u2.rst
@@ -21,4 +21,3 @@ Submodules
   :maxdepth: 4

   paddlespeech.s2t.exps.u2.model
-   paddlespeech.s2t.exps.u2.trainer
--- a/docs/source/api/paddlespeech.s2t.exps.u2.trainer.rst
+++ b/docs/source/api/paddlespeech.s2t.exps.u2.trainer.rst
-paddlespeech.s2t.exps.u2.trainer module
-=======================================
-
-.. automodule:: paddlespeech.s2t.exps.u2.trainer
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.exps.u2_kaldi.bin.recog.rst
+++ b/docs/source/api/paddlespeech.s2t.exps.u2_kaldi.bin.recog.rst
-paddlespeech.s2t.exps.u2\_kaldi.bin.recog module
-================================================
-
-.. automodule:: paddlespeech.s2t.exps.u2_kaldi.bin.recog
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.exps.u2_kaldi.bin.rst
+++ b/docs/source/api/paddlespeech.s2t.exps.u2_kaldi.bin.rst
@@ -12,6 +12,5 @@ Submodules
 .. toctree::
   :maxdepth: 4

-   paddlespeech.s2t.exps.u2_kaldi.bin.recog
   paddlespeech.s2t.exps.u2_kaldi.bin.test
   paddlespeech.s2t.exps.u2_kaldi.bin.train
--- a/docs/source/api/paddlespeech.s2t.training.extensions.rst
+++ b/docs/source/api/paddlespeech.s2t.training.extensions.rst
@@ -15,5 +15,3 @@ Submodules
   paddlespeech.s2t.training.extensions.evaluator
   paddlespeech.s2t.training.extensions.extension
   paddlespeech.s2t.training.extensions.plot
-   paddlespeech.s2t.training.extensions.snapshot
-   paddlespeech.s2t.training.extensions.visualizer
--- a/docs/source/api/paddlespeech.s2t.training.extensions.snapshot.rst
+++ b/docs/source/api/paddlespeech.s2t.training.extensions.snapshot.rst
-paddlespeech.s2t.training.extensions.snapshot module
-====================================================
-
-.. automodule:: paddlespeech.s2t.training.extensions.snapshot
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.training.extensions.visualizer.rst
+++ b/docs/source/api/paddlespeech.s2t.training.extensions.visualizer.rst
-paddlespeech.s2t.training.extensions.visualizer module
-======================================================
-
-.. automodule:: paddlespeech.s2t.training.extensions.visualizer
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.training.updaters.rst
+++ b/docs/source/api/paddlespeech.s2t.training.updaters.rst
@@ -13,5 +13,4 @@ Submodules
   :maxdepth: 4

   paddlespeech.s2t.training.updaters.standard_updater
-   paddlespeech.s2t.training.updaters.trainer
   paddlespeech.s2t.training.updaters.updater
--- a/docs/source/api/paddlespeech.s2t.training.updaters.trainer.rst
+++ b/docs/source/api/paddlespeech.s2t.training.updaters.trainer.rst
-paddlespeech.s2t.training.updaters.trainer module
-=================================================
-
-.. automodule:: paddlespeech.s2t.training.updaters.trainer
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.transform.add_deltas.rst
+++ b/docs/source/api/paddlespeech.s2t.transform.add_deltas.rst
-paddlespeech.s2t.transform.add\_deltas module
-=============================================
-
-.. automodule:: paddlespeech.s2t.transform.add_deltas
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.transform.channel_selector.rst
+++ b/docs/source/api/paddlespeech.s2t.transform.channel_selector.rst
-paddlespeech.s2t.transform.channel\_selector module
-===================================================
-
-.. automodule:: paddlespeech.s2t.transform.channel_selector
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.transform.cmvn.rst
+++ b/docs/source/api/paddlespeech.s2t.transform.cmvn.rst
-paddlespeech.s2t.transform.cmvn module
-======================================
-
-.. automodule:: paddlespeech.s2t.transform.cmvn
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.transform.functional.rst
+++ b/docs/source/api/paddlespeech.s2t.transform.functional.rst
-paddlespeech.s2t.transform.functional module
-============================================
-
-.. automodule:: paddlespeech.s2t.transform.functional
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.transform.perturb.rst
+++ b/docs/source/api/paddlespeech.s2t.transform.perturb.rst
-paddlespeech.s2t.transform.perturb module
-=========================================
-
-.. automodule:: paddlespeech.s2t.transform.perturb
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.transform.rst
+++ b/docs/source/api/paddlespeech.s2t.transform.rst
-paddlespeech.s2t.transform package
-==================================
-
-.. automodule:: paddlespeech.s2t.transform
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-Submodules
----------
-
-.. toctree::
-   :maxdepth: 4
-
-   paddlespeech.s2t.transform.add_deltas
-   paddlespeech.s2t.transform.channel_selector
-   paddlespeech.s2t.transform.cmvn
-   paddlespeech.s2t.transform.functional
-   paddlespeech.s2t.transform.perturb
-   paddlespeech.s2t.transform.spec_augment
-   paddlespeech.s2t.transform.spectrogram
-   paddlespeech.s2t.transform.transform_interface
-   paddlespeech.s2t.transform.transformation
-   paddlespeech.s2t.transform.wpe
--- a/docs/source/api/paddlespeech.s2t.transform.spec_augment.rst
+++ b/docs/source/api/paddlespeech.s2t.transform.spec_augment.rst
-paddlespeech.s2t.transform.spec\_augment module
-===============================================
-
-.. automodule:: paddlespeech.s2t.transform.spec_augment
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.transform.spectrogram.rst
+++ b/docs/source/api/paddlespeech.s2t.transform.spectrogram.rst
-paddlespeech.s2t.transform.spectrogram module
-=============================================
-
-.. automodule:: paddlespeech.s2t.transform.spectrogram
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.transform.transform_interface.rst
+++ b/docs/source/api/paddlespeech.s2t.transform.transform_interface.rst
-paddlespeech.s2t.transform.transform\_interface module
-======================================================
-
-.. automodule:: paddlespeech.s2t.transform.transform_interface
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.transform.transformation.rst
+++ b/docs/source/api/paddlespeech.s2t.transform.transformation.rst
-paddlespeech.s2t.transform.transformation module
-================================================
-
-.. automodule:: paddlespeech.s2t.transform.transformation
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.s2t.transform.wpe.rst
+++ b/docs/source/api/paddlespeech.s2t.transform.wpe.rst
-paddlespeech.s2t.transform.wpe module
-=====================================
-
-.. automodule:: paddlespeech.s2t.transform.wpe
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.server.engine.acs.python.acs_engine.rst
+++ b/docs/source/api/paddlespeech.server.engine.acs.python.acs_engine.rst
-paddlespeech.server.engine.acs.python.acs\_engine module
-========================================================
-
-.. automodule:: paddlespeech.server.engine.acs.python.acs_engine
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.server.engine.acs.python.rst
+++ b/docs/source/api/paddlespeech.server.engine.acs.python.rst
@@ -12,4 +12,3 @@ Submodules
 .. toctree::
   :maxdepth: 4

-   paddlespeech.server.engine.acs.python.acs_engine
--- a/docs/source/api/paddlespeech.server.utils.log.rst
+++ b/docs/source/api/paddlespeech.server.utils.log.rst
-paddlespeech.server.utils.log module
-====================================
-
-.. automodule:: paddlespeech.server.utils.log
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.t2s.exps.rst
+++ b/docs/source/api/paddlespeech.t2s.exps.rst
@@ -30,10 +30,10 @@ Submodules

   paddlespeech.t2s.exps.inference
   paddlespeech.t2s.exps.inference_streaming
+   paddlespeech.t2s.models.vits.monotonic_align
   paddlespeech.t2s.exps.ort_predict
   paddlespeech.t2s.exps.ort_predict_e2e
   paddlespeech.t2s.exps.ort_predict_streaming
-   paddlespeech.t2s.exps.stream_play_tts
   paddlespeech.t2s.exps.syn_utils
   paddlespeech.t2s.exps.synthesize
   paddlespeech.t2s.exps.synthesize_e2e

--- a/docs/source/api/paddlespeech.t2s.exps.stream_play_tts.rst
+++ b/docs/source/api/paddlespeech.t2s.exps.stream_play_tts.rst
-paddlespeech.t2s.exps.stream\_play\_tts module
-==============================================
-
-.. automodule:: paddlespeech.t2s.exps.stream_play_tts
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.t2s.models.ernie_sat.mlm.rst
+++ b/docs/source/api/paddlespeech.t2s.models.ernie_sat.mlm.rst
-paddlespeech.t2s.models.ernie\_sat.mlm module
-=============================================
-
-.. automodule:: paddlespeech.t2s.models.ernie_sat.mlm
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.core.rst
+++ b/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.core.rst
-paddlespeech.t2s.models.vits.monotonic\_align.core module
-=========================================================
-
-.. automodule:: paddlespeech.t2s.models.vits.monotonic_align.core
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.rst
+++ b/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.rst
-paddlespeech.t2s.models.vits.monotonic\_align package
-=====================================================
-
-.. automodule:: paddlespeech.t2s.models.vits.monotonic_align
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-Submodules
----------
-
-.. toctree::
-   :maxdepth: 4
-
-   paddlespeech.t2s.models.vits.monotonic_align.core
-   paddlespeech.t2s.models.vits.monotonic_align.setup
--- a/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.setup.rst
+++ b/docs/source/api/paddlespeech.t2s.models.vits.monotonic_align.setup.rst
-paddlespeech.t2s.models.vits.monotonic\_align.setup module
-==========================================================
-
-.. automodule:: paddlespeech.t2s.models.vits.monotonic_align.setup
-   :members:
-   :undoc-members:
-   :show-inheritance:
--- a/docs/source/api/paddlespeech.t2s.models.vits.rst
+++ b/docs/source/api/paddlespeech.t2s.models.vits.rst
@@ -12,7 +12,6 @@ Subpackages
 .. toctree::
   :maxdepth: 4

-   paddlespeech.t2s.models.vits.monotonic_align
   paddlespeech.t2s.models.vits.wavenet

 Submodules

--- a/docs/source/tts/demo.rst
+++ b/docs/source/tts/demo.rst
--- a/docs/source/tts/demo_2.rst
+++ b/docs/source/tts/demo_2.rst
@@ -19,7 +19,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
        <tr>
            <td>早上好，今天是2020/10/29，最低温度是-3°C。</td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/001.wav"
                        type="audio/wav">
@@ -27,7 +27,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
                </audio>
            </td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav"
                        type="audio/wav">
@@ -38,7 +38,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
        <tr>
            <td>你好，我的编号是37249，很高兴为您服务。</td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/002.wav"
                        type="audio/wav">
@@ -46,7 +46,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
                </audio>
            </td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/002.wav"
                        type="audio/wav">
@@ -57,7 +57,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
        <tr>
            <td>我们公司有37249个人。</td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/003.wav"
                        type="audio/wav">
@@ -65,7 +65,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
                </audio>
            </td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/003.wav"
                        type="audio/wav">
@@ -76,7 +76,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
        <tr>
            <td>我出生于2005年10月8日。</td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/004.wav"
                        type="audio/wav">
@@ -84,7 +84,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
                </audio>
            </td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/004.wav"
                        type="audio/wav">
@@ -95,7 +95,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
        <tr>
            <td>我们习惯在12:30吃中午饭。</td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/005.wav"
                        type="audio/wav">
@@ -103,7 +103,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
                </audio>
            </td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/005.wav"
                        type="audio/wav">
@@ -114,7 +114,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
        <tr>
            <td>只要有超过3/4的人投票同意，你就会成为我们的新班长。</td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/006.wav"
                        type="audio/wav">
@@ -122,7 +122,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
                </audio>
            </td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/006.wav"
                        type="audio/wav">
@@ -133,7 +133,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
        <tr>
            <td>我要买一只价值999.9元的手表。</td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/007.wav"
                        type="audio/wav">
@@ -141,7 +141,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
                </audio>
            </td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/007.wav"
                        type="audio/wav">
@@ -152,7 +152,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
        <tr>
            <td>我的手机号是18544139121，欢迎来电。</td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/008.wav"
                        type="audio/wav">
@@ -160,7 +160,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
                </audio>
            </td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/008.wav"
                        type="audio/wav">
@@ -171,7 +171,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
        <tr>
            <td>明天有62%的概率降雨。</td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/009.wav"
                        type="audio/wav">
@@ -179,7 +179,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
                </audio>
            </td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/009.wav"
                        type="audio/wav">
@@ -190,7 +190,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
        <tr>
            <td>手表厂有五种好产品。</td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/010.wav"
                        type="audio/wav">
@@ -198,7 +198,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
                </audio>
            </td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/010.wav"
                        type="audio/wav">
@@ -209,7 +209,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
        <tr>
            <td>跑马场有五百匹很勇敢的千里马。</td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/011.wav"
                        type="audio/wav">
@@ -217,7 +217,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
                </audio>
            </td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/011.wav"
                        type="audio/wav">
@@ -228,7 +228,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
        <tr>
            <td>有一天，我看到了一栋楼，我顿感不妙，因为我看不清里面有没有人。</td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/012.wav"
                        type="audio/wav">
@@ -236,7 +236,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
                </audio>
            </td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/012.wav"
                        type="audio/wav">
@@ -247,7 +247,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
        <tr>
            <td>史小姐拿着小雨伞去找她的老保姆了。</td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/013.wav"
                        type="audio/wav">
@@ -255,7 +255,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
                </audio>
            </td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/013.wav"
                        type="audio/wav">
@@ -266,7 +266,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
        <tr>
            <td>不要相信这个老奶奶说的话，她一点儿也不好。</td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/014.wav"
                        type="audio/wav">
@@ -274,7 +274,7 @@ FastSpeech2 + Parallel WaveGAN in CSMSC
                </audio>
            </td>
            <td>
-                <audio controls="controls">
+                <audio controls="controls" style="width: 220px;">
                    <source
                        src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/014.wav"
                        type="audio/wav">

--- a/examples/other/mfa/run.sh
+++ b/examples/other/mfa/run.sh
@@ -39,7 +39,7 @@ fi
 export PATH="$MFA_DOWNLOAD_DIR/montreal-forced-aligner/bin"
 if [ ! -d "$EXP_DIR/baker_alignment" ]; then
    echo "Start MFA training..."
-    mfa_train_and_align $EXP_DIR/baker_corpus "$EXP_DIR/$LEXICON_NAME.lexicon" $EXP_DIR/baker_alignment -o $EXP_DIR/baker_model --clean --verbose --temp_directory exp/.mfa_train_and_align
+    mfa_train_and_align $EXP_DIR/baker_corpus "$EXP_DIR/$LEXICON_NAME.lexicon" $EXP_DIR/baker_alignment -o $EXP_DIR/baker_model --clean --verbose --temp_directory $EXP_DIR/.mfa_train_and_align
    echo "training done!"
    echo "results: $EXP_DIR/baker_alignment"
    echo "model: $EXP_DIR/baker_model"