Adds ollama to requirements and removes parlerTTS from models.

TTS_models.py

@@ -63,25 +63,25 @@ class Bark(TTSModel):
 ####################################################
 # pip install git+https://github.com/huggingface/parler-tts.git
 
-from parler_tts import ParlerTTSForConditionalGeneration
-from transformers import AutoTokenizer
-
-class ParlerTTS(TTSModel):
-    def __init__(self, name="parler-tts/parler-tts-large-v1"):
-        super(ParlerTTS, self).__init__(name)
-        self.description = "A female speaker delivers a slightly expressive and animated speech with a moderate speed and pitch. The recording is of very high quality, with the speaker's voice sounding clear and very close up."
-        self.model = ParlerTTSForConditionalGeneration.from_pretrained(self.hf_name).to(self.device)
-        self.tokenizer = AutoTokenizer.from_pretrained(self.hf_name)
-        # self.synthesiser = pipeline("text-to-speech", model=self.model, tokenizer=self.tokenizer, device=self.device)
+# from parler_tts import ParlerTTSForConditionalGeneration
+# from transformers import AutoTokenizer
 
-    def synthesize(self, text):
-        input_ids = self.tokenizer(self.description, return_tensors="pt").input_ids.to(self.device)
-        prompt_input_ids = self.tokenizer(text, return_tensors="pt").input_ids.to(self.device)
+# class ParlerTTS(TTSModel):
+#     def __init__(self, name="parler-tts/parler-tts-large-v1"):
+#         super(ParlerTTS, self).__init__(name)
+#         self.description = "A female speaker delivers a slightly expressive and animated speech with a moderate speed and pitch. The recording is of very high quality, with the speaker's voice sounding clear and very close up."
+#         self.model = ParlerTTSForConditionalGeneration.from_pretrained(self.hf_name).to(self.device)
+#         self.tokenizer = AutoTokenizer.from_pretrained(self.hf_name)
+#         # self.synthesiser = pipeline("text-to-speech", model=self.model, tokenizer=self.tokenizer, device=self.device)
 
-        generation = self.model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids)
-        speech = generation.cpu().numpy().squeeze()
-        print("[ParlerTTS - synthesize]", speech)
-        return speech
+#     def synthesize(self, text):
+#         input_ids = self.tokenizer(self.description, return_tensors="pt").input_ids.to(self.device)
+#         prompt_input_ids = self.tokenizer(text, return_tensors="pt").input_ids.to(self.device)
+
+#         generation = self.model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids)
+#         speech = generation.cpu().numpy().squeeze()
+#         print("[ParlerTTS - synthesize]", speech)
+#         return speech
 
 ####################################################
 # PENDING: NOT WORKING FROM HF

requirements.txt

@@ -5,4 +5,5 @@ transformers
 gradio
 pypdf
 emoji
-coqui-tts
+coqui-tts
+ollama