add Cli Cantonese onnx

paddlespeech/cli/tts/infer.py

@@ -46,6 +46,7 @@ ONNX_SUPPORT_SET = {
     'fastspeech2_vctk',
     'fastspeech2_male',
     'fastspeech2_mix',
+    'fastspeech2_canton',
     'pwgan_csmsc',
     'pwgan_ljspeech',
     'pwgan_aishell3',
@@ -535,7 +536,7 @@ class TTSExecutor(BaseExecutor):
             part_phone_ids = phone_ids[i]
             if am_name == 'fastspeech2':
                 am_input_feed.update({'text': part_phone_ids})
-                if am_dataset in {"aishell3", "vctk", "mix"}:
+                if am_dataset in {"aishell3", "vctk", "mix", "canton"}:
                     # NOTE: 'spk_id' should be List[int] rather than int here!!
                     am_input_feed.update({'spk_id': [spk_id]})
             elif am_name == 'speedyspeech':

paddlespeech/resource/pretrained_models.py

@@ -1459,6 +1459,24 @@ tts_static_pretrained_models = {
             24000,
         },
     },
+    "fastspeech2_canton": {
+        '1.0': {
+            'url':
+            'https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_canton_static_1.4.0.zip',
+            'md5':
+            'd320a99b2f90e3b206271f9a0128671c',
+            'model':
+            'fastspeech2_canton.pdmodel',
+            'params':
+            'fastspeech2_canton.pdiparams',
+            'phones_dict':
+            'phone_id_map.txt',
+            'speaker_dict':
+            'speaker_id_map.txt',
+            'sample_rate':
+            24000,
+        },
+    },
     # pwgan
     "pwgan_csmsc-zh": {
         '1.0': {
@@ -1626,6 +1644,8 @@ tts_static_pretrained_models["pwgan_male-en"] = tts_static_pretrained_models[
     "pwgan_male-mix"] = tts_static_pretrained_models["pwgan_male-zh"]
 tts_static_pretrained_models["hifigan_male-en"] = tts_static_pretrained_models[
     "hifigan_male-mix"] = tts_static_pretrained_models["hifigan_male-zh"]
+tts_static_pretrained_models["pwgan_aishell3-canton"] = tts_static_pretrained_models[
+    "pwgan_aishell3-zh"]
 
 tts_onnx_pretrained_models = {
     # speedyspeech
@@ -1797,6 +1817,22 @@ tts_onnx_pretrained_models = {
             24000,
         },
     },
+    "fastspeech2_canton_onnx": {
+        '1.0': {
+            'url':
+            'https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_canton_onnx_1.4.0.zip',
+            'md5':
+            'fea22a06ece005345a7148ba679b024c',
+            'ckpt':
+            'fastspeech2_canton.onnx',
+            'phones_dict':
+            'phone_id_map.txt',
+            'speaker_dict':
+            'speaker_id_map.txt',
+            'sample_rate':
+            24000,
+        },
+    },
     # pwgan
     "pwgan_csmsc_onnx-zh": {
         '1.0': {
@@ -1943,6 +1979,8 @@ tts_onnx_pretrained_models["pwgan_male_onnx-en"] = tts_onnx_pretrained_models[
 tts_onnx_pretrained_models["hifigan_male_onnx-en"] = tts_onnx_pretrained_models[
     "hifigan_male_onnx-mix"] = tts_onnx_pretrained_models[
         "hifigan_male_onnx-zh"]
+tts_onnx_pretrained_models["pwgan_aishell3_onnx-canton"] = tts_onnx_pretrained_models[
+    "pwgan_aishell3_onnx-zh"]
 
 # ---------------------------------
 # ------------ Vector -------------

paddlespeech/t2s/exps/inference.py

@@ -45,6 +45,7 @@ def parse_args():
             'fastspeech2_male-zh',
             'fastspeech2_male-en',
             'fastspeech2_male-mix',
+            'fastspeech2_canton',
         ],
         help='Choose acoustic model type of tts task.')
     parser.add_argument(