fix a config key error (#110 )

bump version string to 0.3.0
Merge branch 'develop' of https://github.com/PaddlePaddle/Parakeet into develop
2021-05-18 18:13:36 +08:00 · 2021-05-17 11:33:39 +08:00 · 2021-05-17 11:29:31 +08:00 · 2021-05-13 17:06:34 +08:00 · 2021-05-13 16:22:56 +08:00 · 2021-05-11 22:46:09 +08:00
4 changed files with 4 additions and 4 deletions
--- a/examples/transformer_tts/config.py
+++ b/examples/transformer_tts/config.py
@ -39,7 +39,7 @@ _C.model = CN(
        d_ffn=1024,  # encoder_d_ffn & decoder_d_ffn
        encoder_layers=4,  # number of transformer encoder layer
        decoder_layers=4,  # number of transformer decoder layer
-        d_prenet=256,  # decprenet's hidden size (d_mel=>d_prenet=>d_decoder)
+        d_prenet=256,  # decoder prenet's hidden size (n_mels=>d_prenet=>d_decoder)
        d_postnet=256,  # decoder postnet(cnn)'s internal channel
        postnet_layers=5,  # decoder postnet(cnn)'s layer
        postnet_kernel_size=5,  # decoder postnet(cnn)'s kernel size
--- a/examples/transformer_tts/preprocess.py
+++ b/examples/transformer_tts/preprocess.py
@ -38,7 +38,7 @@ def create_dataset(config, source_path, target_path, verbose=False):
    processor = AudioProcessor(
        sample_rate=config.data.sample_rate,
        n_fft=config.data.n_fft,
-        n_mels=config.data.d_mel,
+        n_mels=config.data.n_mels,
        win_length=config.data.win_length,
        hop_length=config.data.hop_length,
        fmax=config.data.fmax,
--- a/parakeet/init.py
+++ b/parakeet/init.py
@ -12,6 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.

-__version__ = "0.2.0-beta.0"
+__version__ = "0.3.0"

 from parakeet import audio, data, datasets, frontend, models, modules, training, utils
--- a/parakeet/models/transformer_tts.py
+++ b/parakeet/models/transformer_tts.py
@ -571,7 +571,7 @@ class TransformerTTS(nn.Layer):
            frontend,
            d_encoder=config.model.d_encoder,
            d_decoder=config.model.d_decoder,
-            d_mel=config.data.d_mel,
+            d_mel=config.data.n_mels,
            n_heads=config.model.n_heads,
            d_ffn=config.model.d_ffn,
            encoder_layers=config.model.encoder_layers,
Author	SHA1	Message	Date
Feiyu Chan	d726863138	fix a config key error (#110 )	2021-05-18 18:13:36 +08:00
chenfeiyu	fa6ddf5b0c	bump version string to 0.3.0	2021-05-17 11:33:39 +08:00
chenfeiyu	c02adfdad8	Merge branch 'develop' of https://github.com/PaddlePaddle/Parakeet into develop	2021-05-17 11:29:31 +08:00
chenfeiyu	e1a7c296fe	simplify text processing code and update notebook	2021-05-13 17:06:34 +08:00
chenfeiyu	6a1fb158d9	format code with pre-commit	2021-05-13 16:22:56 +08:00
chenfeiyu	73ca693395	add praatio into requirements for running the experiments	2021-05-11 22:46:09 +08:00
chenfeiyu	2f644e1b8b	refine READMEs and clean code	2021-05-11 22:44:02 +08:00
chenfeiyu	8bcbcf8a86	add links to downlaod pretrained models	2021-05-07 16:49:11 +08:00
chenfeiyu	71a87559da	update README	2021-05-07 16:28:23 +08:00
chenfeiyu	664fc20c0a	update doc	2021-05-07 16:16:58 +08:00
chenfeiyu	b9aa61b5eb	update docstrings for tacotron	2021-05-07 16:08:31 +08:00
chenfeiyu	f197e4d04f	update README and doc	2021-05-07 15:35:47 +08:00
chenfeiyu	ef1ea56ed6	fix typos and docs	2021-05-07 15:03:54 +08:00
chenfeiyu	38831bf8b6	add extra_config keys into the default config of tacotron	2021-04-30 14:27:08 +08:00
chenfeiyu	b88a0f90aa	add STFT back	2021-04-29 17:54:07 +08:00
iclementine	42092f1f5b	update README for examples/ge2e	2021-04-29 17:15:18 +08:00
iclementine	b1304cb449	add images for exampels/tacotron2_aishell3's README	2021-04-29 17:09:40 +08:00
iclementine	cab12c2dfd	update tacotron_aishell3's README	2021-04-29 17:00:26 +08:00
iclementine	ba7639b994	update tacotron2	2021-04-29 16:43:03 +08:00
iclementine	123bbe994f	update tacotron2 from_pretrained, update setup.py	2021-04-29 16:04:32 +08:00
iclementine	701376f401	remove tacotron2_msp	2021-04-28 20:05:12 +08:00
iclementine	77eb13d95d	format code	2021-04-28 20:02:29 +08:00
chenfeiyu	cbe531158e	add plot_multiple_attentions and update visualization code in transformer_tts	2021-04-27 17:40:50 +08:00
chenfeiyu	263d3eb88b	add an optional to alter the loss and model structure of tacotron2, add an alternative config	2021-04-26 21:18:29 +08:00
chenfeiyu	4fc86abf5a	Merge branch 'baker' of https://github.com/iclementine/Parakeet into baker	2021-04-25 11:11:36 +08:00
chenfeiyu	85649725fb	add voice cloning notebook	2021-04-25 11:11:24 +08:00
iclementine	cf01a0da22	add more details to thr README, fix some preprocess scripts	2021-04-25 11:00:42 +08:00
iclementine	4426417da1	WIP: add README	2021-04-22 17:40:36 +08:00
iclementine	e8a9a118bb	clean code for data processing	2021-04-22 17:20:34 +08:00
iclementine	56f2552201	fix argument name	2021-04-22 14:50:52 +08:00
chenfeiyu	c2560e8aa2	fix argument order	2021-04-22 13:46:51 +08:00
iclementine	3a744dbf30	clean code	2021-04-22 13:25:25 +08:00
iclementine	764c35e99e	move tacotron2_msp	2021-04-22 11:00:33 +08:00
chenfeiyu	c8627fdd75	remove imports to deleted modules	2021-04-20 20:12:57 +08:00
chenfeiyu	16b4d4eecb	remove files not included in this release	2021-04-20 17:12:22 +08:00
chenfeiyu	6b3999217b	remove imports that are removed	2021-04-20 15:54:55 +08:00
iclementine	e992e17456	resolve conflict	2021-04-19 20:17:21 +08:00
iclementine	0eea7cc373	fix typos	2021-04-19 20:15:46 +08:00
iclementine	f8f3ec4709	Merge branch 'baker' of github.com:iclementine/Parakeet into baker	2021-04-19 20:12:07 +08:00
chenfeiyu	9da118e53b	merge wavenet	2021-04-19 20:09:01 +08:00
chenfeiyu	3741cc49ca	change wavenet to use on-the-fly prepeocessing	2021-04-19 19:58:36 +08:00
iclementine	b53b274585	change batch_text_id, batch_spec, batch_wav to include valid lengths in the returned value	2021-04-19 17:06:52 +08:00
iclementine	6749ce40ea	add audio datasets	2021-04-19 16:17:30 +08:00
iclementine	49f2c4b3fb	change stft to use conv1d	2021-04-16 15:01:10 +08:00
iclementine	e06c6cdfe1	WIP:update hifigan	2021-04-15 17:23:42 +08:00
iclementine	68497f89a4	WIP: add hifigan	2021-04-14 20:59:26 +08:00
chenfeiyu	e54f23befd	update collate function, data loader not does not convert nested list into numpy array.	2021-04-14 20:51:13 +08:00
chenfeiyu	c6965e2c5a	fix fmax for example/waveflow	2021-04-14 20:50:38 +08:00
iclementine	b674f63d74	add 2 frontend	2021-04-08 04:59:29 +08:00
iclementine	184745f42b	add gst layer	2021-04-08 04:59:03 +08:00
iclementine	dc3b798f82	add global condition support for tacotron2	2021-04-08 04:58:44 +08:00
chenfeiyu	5011f16c10	minor fix	2021-04-07 10:55:05 +08:00
iclementine	4d3014f4d5	add new trainer	2021-04-03 16:19:46 +08:00
iclementine	27e0201d0d	format code for tacotron_vctk, add plot_waveform to display	2021-04-02 15:46:28 +08:00
iclementine	a3fae49022	merge refactor_tacotron	2021-04-02 11:48:16 +08:00
iclementine	274d8dce07	update experiment and display	2021-04-02 11:37:48 +08:00
iclementine	15b205d6e0	Merge branch 'develop' into baker	2021-04-02 11:23:21 +08:00
chenfeiyu	8d67066765	add example for baker and aishell3	2021-04-02 11:06:34 +08:00
chenfeiyu	9babec0f98	fix text log extention name	2021-04-01 13:49:52 +08:00
chenfeiyu	752272de98	fix bugs	2021-04-01 13:15:06 +08:00
iclementine	e0052ccedf	fix typos	2021-03-31 19:38:12 +08:00
iclementine	a834e132b9	fix root path	2021-03-31 19:36:48 +08:00
iclementine	dd73ee6611	fix root path	2021-03-31 19:35:59 +08:00
iclementine	883bc16d24	fix root path	2021-03-31 19:33:33 +08:00
iclementine	9798d07337	fix visualizer	2021-03-31 19:32:23 +08:00
iclementine	f84d460613	fix class name	2021-03-31 19:31:16 +08:00
iclementine	327c7a5ce4	fix indentation	2021-03-31 19:29:09 +08:00
iclementine	4a039b6407	add vctk example for refactored tacotron	2021-03-31 17:34:19 +08:00
iclementine	7cc3e8c340	add a simple strategy to support multispeaker for tacotron.	2021-03-31 15:23:41 +08:00
iclementine	2dd393349f	Merge branch 'develop' into refactor_tacotron	2021-03-30 16:01:22 +08:00
iclementine	e3f7bb5a51	simplify visualization code	2021-03-30 15:56:14 +08:00
chenfeiyu	0fdb86834b	Merge branch 'develop' into baker	2021-03-30 14:39:11 +08:00
chenfeiyu	b5dd0cc197	fix speaker encoder and add support for 2 more datasets	2021-03-30 14:38:44 +08:00
iclementine	4757f08550	Merge branch 'develop' into baker	2021-03-29 11:17:51 +08:00
iclementine	59ed247840	fix lstm speaker encoder	2021-03-29 11:17:23 +08:00
iclementine	ab85d5ca13	Merge branch 'develop' into baker	2021-03-29 11:13:57 +08:00
iclementine	5443e23fb7	fix lstm speaker encoder	2021-03-29 11:12:02 +08:00
iclementine	6defef4944	Merge branch 'baker' of github.com:iclementine/Parakeet into baker	2021-03-29 10:49:24 +08:00
chenfeiyu	489fb69f55	Merge branch 'develop' into baker	2021-03-29 10:49:34 +08:00
iclementine	a9a78742fa	Merge branch 'develop' into baker	2021-03-29 10:42:17 +08:00
iclementine	2475da3322	add ge2e	2021-03-27 17:39:37 +08:00
chenfeiyu	a005cc88a3	WIP: baker	2021-03-27 12:43:03 +08:00
iclementine	2b62fbb614	1. change the default min value of LogMagnitude to 1e-5; 2. remove stop logit prediction from tacotron2 model.	2021-03-23 10:44:22 +08:00
iclementine	da63cfa42e	add an embedding layer.	2021-03-22 21:39:22 +08:00
iclementine	f9d6160916	add an option to normalize volume when loading audio.	2021-03-22 21:38:28 +08:00
iclementine	086fbf8e35	refactoring code	2021-03-22 21:23:46 +08:00
chenfeiyu	3c60fec900	remove bn in postnet	2021-02-27 03:26:41 +08:00
chenfeiyu	929165b64a	1. remove space from numericalized representation; 2. fix decoder paddign mask's unsqueeze dim.	2021-02-27 02:59:38 +08:00
chenfeiyu	ae9e218073	use emb add in tacotron2	2021-02-26 18:08:26 +08:00
chenfeiyu	40237c40b0	Merge branch 'develop' of https://github.com/PaddlePaddle/Parakeet into baker	2021-02-26 11:07:03 +08:00
chenfeiyu	9e4d5a3d8a	fix experiments for waveflow and wavenet, only write visual log in rank-0	2021-02-21 17:30:13 +08:00
chenfeiyu	6a92fde9b2	Merge branch 'develop' of https://github.com/PaddlePaddle/Parakeet into baker	2021-02-18 19:58:27 +08:00
chenfeiyu	25bd8987a6	Merge branch 'develop' of https://github.com/PaddlePaddle/Parakeet into baker	2021-02-18 19:51:56 +08:00
chenfeiyu	239703be8b	hacky thing, add tone support for acoustic model	2021-02-10 22:58:08 +08:00