Merge pull request #102 from lenML/dev_tts_pipeline

Dev tts pipeline
lenML · Jul 13, 2024 · 4028da1 · 4028da1
2 parents bfc3789 + 846d18f
commit 4028da1
Show file tree

Hide file tree

Showing 108 changed files with 2,562 additions and 1,414 deletions.
diff --git a/data/load_json_spk.py b/data/load_json_spk.py
@@ -1,6 +1,6 @@
 import json
 
-from modules.speaker import speaker_mgr
+from modules.core.speaker import speaker_mgr
 
 # 出处: https://github.com/2noise/ChatTTS/issues/238
 data = json.load(open("./data/slct_voice_240605.json", "r"))

diff --git a/modules/ChatTTS/ChatTTS/model/gpt.py b/modules/ChatTTS/ChatTTS/model/gpt.py
@@ -545,23 +545,35 @@ def generate(
                         if show_tqdm:
                             pbar.close()
                         self.logger.warn("regenerate in order to ensure non-empty")
+                        del_all(attentions)
+                        del_all(hiddens)
+                        del (
+                            start_idx,
+                            end_idx,
+                            finish,
+                            temperature,
+                            attention_mask_cache,
+                            past_key_values,
+                            idx_next,
+                            inputs_ids_tmp,
+                        )
                         new_gen = self.generate(
-                            emb,
-                            inputs_ids,
-                            old_temperature,
-                            eos_token,
-                            attention_mask,
-                            max_new_token,
-                            min_new_token,
-                            logits_warpers,
-                            logits_processors,
-                            infer_text,
-                            return_attn,
-                            return_hidden,
-                            stream,
-                            show_tqdm,
-                            ensure_non_empty,
-                            context,
+                            emb=emb,
+                            inputs_ids=inputs_ids,
+                            old_temperature=old_temperature,
+                            eos_token=eos_token,
+                            attention_mask=attention_mask,
+                            max_new_token=max_new_token,
+                            min_new_token=min_new_token,
+                            logits_warpers=logits_warpers,
+                            logits_processors=logits_processors,
+                            infer_text=infer_text,
+                            return_attn=return_attn,
+                            return_hidden=return_hidden,
+                            stream=stream,
+                            show_tqdm=show_tqdm,
+                            ensure_non_empty=ensure_non_empty,
+                            context=context,
                         )
                         for result in new_gen:
                             yield result

diff --git a/modules/api/impl/google_api.py b/modules/api/impl/google_api.py
@@ -5,12 +5,12 @@
 
 from modules.api import utils as api_utils
 from modules.api.Api import APIManager
-from modules.api.impl.handler.SSMLHandler import SSMLHandler
-from modules.api.impl.handler.TTSHandler import TTSHandler
-from modules.api.impl.model.audio_model import AdjustConfig, AudioFormat
-from modules.api.impl.model.chattts_model import ChatTTSConfig, InferConfig
-from modules.api.impl.model.enhancer_model import EnhancerConfig
-from modules.speaker import Speaker, speaker_mgr
+from modules.core.handler.datacls.audio_model import AdjustConfig, AudioFormat
+from modules.core.handler.datacls.chattts_model import ChatTTSConfig, InferConfig
+from modules.core.handler.datacls.enhancer_model import EnhancerConfig
+from modules.core.handler.SSMLHandler import SSMLHandler
+from modules.core.handler.TTSHandler import TTSHandler
+from modules.core.speaker import Speaker, speaker_mgr
 
 
 class SynthesisInput(BaseModel):

diff --git a/modules/api/impl/handler/AudioHandler.py b/modules/api/impl/handler/AudioHandler.py
diff --git a/modules/api/impl/handler/SSMLHandler.py b/modules/api/impl/handler/SSMLHandler.py