Fix some error

FIX:
    llm_provider.py 102: _model -> model
MOD:
    utility.py 25: add windows termial color print
    text_to_speech.py 29: add windows version
ADD:
    add termcolor in requirements.txt
This commit is contained in:
steveh8758_lab 2025-02-23 19:37:57 +08:00
parent 298c26a63f
commit 42d2655881
4 changed files with 51 additions and 25 deletions

View File

@ -8,4 +8,6 @@ torch==2.5.1
ollama==0.4.7 ollama==0.4.7
scipy==1.15.1 scipy==1.15.1
kokoro==0.7.12 kokoro==0.7.12
flask==3.1.0 flask==3.1.0
soundfile==0.13.1
termcolor

View File

@ -11,7 +11,7 @@ class Provider:
def __init__(self, provider_name, model, server_address = "127.0.0.1:5000"): def __init__(self, provider_name, model, server_address = "127.0.0.1:5000"):
self.provider_name = provider_name.lower() self.provider_name = provider_name.lower()
self.model = model self.model = model
self.server = self.check_address_format(server_address) self.server = self.check_address_format(server_address)
self.available_providers = { self.available_providers = {
"ollama": self.ollama_fn, "ollama": self.ollama_fn,
"server": self.server_fn, "server": self.server_fn,
@ -25,7 +25,7 @@ class Provider:
def check_address_format(self, address): def check_address_format(self, address):
""" """
Validate if the address is valid IP. Validate if the address is valid IP.
""" """
try: try:
ip, port = address.rsplit(":", 1) ip, port = address.rsplit(":", 1)
@ -35,7 +35,7 @@ class Provider:
except ValueError as e: except ValueError as e:
raise Exception(f"Invalid address format: {e}") raise Exception(f"Invalid address format: {e}")
return address return address
def respond(self, history, verbose = True): def respond(self, history, verbose = True):
""" """
Use the choosen provider to generate text. Use the choosen provider to generate text.
@ -61,7 +61,7 @@ class Provider:
except Exception as e: except Exception as e:
print(f"An error occurred: {e}") print(f"An error occurred: {e}")
return False return False
def server_fn(self, history, verbose = True): def server_fn(self, history, verbose = True):
""" """
Use a remote server wit LLM to generate text. Use a remote server wit LLM to generate text.
@ -99,12 +99,12 @@ class Provider:
thought += chunk['message']['content'] thought += chunk['message']['content']
except ollama.ResponseError as e: except ollama.ResponseError as e:
if e.status_code == 404: if e.status_code == 404:
ollama.pull(self._model) ollama.pull(self.model)
if "refused" in str(e): if "refused" in str(e):
raise Exception("Ollama connection failed. is the server running ?") raise Exception("Ollama connection failed. is the server running ?")
raise e raise e
return thought return thought
def test_fn(self, history, verbose = True): def test_fn(self, history, verbose = True):
""" """
Test function to generate text. Test function to generate text.
@ -121,4 +121,4 @@ class Provider:
echo "Hello world from bash" echo "Hello world from bash"
``` ```
""" """
return thought return thought

View File

@ -3,11 +3,13 @@ from IPython.display import display, Audio
import soundfile as sf import soundfile as sf
import subprocess import subprocess
import re import re
import platform
class Speech(): class Speech():
def __init__(self, language = "english") -> None: def __init__(self, language = "english") -> None:
self.lang_map = { self.lang_map = {
"english": 'a', # 🇺🇸 'a' => American English "english": 'a', # 🇺🇸 'a' => American English
"chinese": 'z', # 🇯🇵 'j' => Japanese: pip install misaki[ja] "chinese": 'z', # 🇯🇵 'j' => Japanese: pip install misaki[ja]
"japanese": 'j' # # 🇨🇳 'z' => Mandarin Chinese: pip install misaki[zh] "japanese": 'j' # # 🇨🇳 'z' => Mandarin Chinese: pip install misaki[zh]
} }
@ -20,11 +22,16 @@ class Speech():
speed=1, split_pattern=r'\n+' speed=1, split_pattern=r'\n+'
) )
for i, (gs, ps, audio) in enumerate(generator): for i, (gs, ps, audio) in enumerate(generator):
audio_file = f'sample.wav' audio_file = 'sample.wav'
print(audio_file)
display(Audio(data=audio, rate=24000, autoplay=i==0)) display(Audio(data=audio, rate=24000, autoplay=i==0))
sf.write(audio_file, audio, 24000) # save each audio file sf.write(audio_file, audio, 24000) # save each audio file
subprocess.call(["afplay", audio_file]) if platform.system().lower() != "windows":
subprocess.call(["afplay", audio_file])
else:
import winsound
winsound.PlaySound(audio_file, winsound.SND_FILENAME)
def clean_sentence(self, sentence): def clean_sentence(self, sentence):
sentence = re.sub(r'`.*?`', '', sentence) sentence = re.sub(r'`.*?`', '', sentence)
sentence = re.sub(r'[^a-zA-Z0-9.,!? ]+', '', sentence) sentence = re.sub(r'[^a-zA-Z0-9.,!? ]+', '', sentence)

View File

@ -1,20 +1,37 @@
from colorama import Fore from colorama import Fore
from termcolor import colored
import platform
def pretty_print(text, color = "info"): def pretty_print(text, color = "info"):
""" """
print text with color print text with color
""" """
color_map = { if platform.system().lower() != "windows":
"success": Fore.GREEN, color_map = {
"failure": Fore.RED, "success": Fore.GREEN,
"status": Fore.LIGHTGREEN_EX, "failure": Fore.RED,
"code": Fore.LIGHTBLUE_EX, "status": Fore.LIGHTGREEN_EX,
"warning": Fore.YELLOW, "code": Fore.LIGHTBLUE_EX,
"output": Fore.LIGHTCYAN_EX, "warning": Fore.YELLOW,
} "output": Fore.LIGHTCYAN_EX,
if color not in color_map: }
print(text) if color not in color_map:
pretty_print("Invalid color in pretty_print", "warning") print(text)
return pretty_print("Invalid color in pretty_print", "warning")
print(color_map[color], text, Fore.RESET) return
print(color_map[color], text, Fore.RESET)
else:
color_map = {
"success": "green",
"failure": "red",
"status": "light_green",
"code": "light_blue",
"warning": "yello",
"output": "cyan",
"default": "black"
}
if color not in color_map:
color = "default"
print(colored(text, color_map[color]))