chore(tools): rename wav_arr_to_mp3_view to pcm_arr_to_mp3_view

examples/api/main.py

@@ -17,7 +17,7 @@ from typing import Optional
 
 import ChatTTS
 
-from tools.audio import wav_arr_to_mp3_view
+from tools.audio import pcm_arr_to_mp3_view
 from tools.logger import get_logger
 import torch
 
@@ -101,7 +101,7 @@ async def generate_voice(params: ChatTTSParams):
         buf, "a", compression=zipfile.ZIP_DEFLATED, allowZip64=False
     ) as f:
         for idx, wav in enumerate(wavs):
-            f.writestr(f"{idx}.mp3", wav_arr_to_mp3_view(wav))
+            f.writestr(f"{idx}.mp3", pcm_arr_to_mp3_view(wav))
     logger.info("Audio generation successful.")
     buf.seek(0)
 

examples/cmd/run.py

@@ -13,14 +13,14 @@ import numpy as np
 
 import ChatTTS
 
-from tools.audio import wav_arr_to_mp3_view
+from tools.audio import pcm_arr_to_mp3_view
 from tools.logger import get_logger
 
 logger = get_logger("Command")
 
 
 def save_mp3_file(wav, index):
-    data = wav_arr_to_mp3_view(wav)
+    data = pcm_arr_to_mp3_view(wav)
     mp3_filename = f"output_audio_{index}.mp3"
     with open(mp3_filename, "wb") as f:
         f.write(data)

examples/web/funcs.py

@@ -4,7 +4,6 @@ from typing import Optional
 from time import sleep
 
 import gradio as gr
-import numpy as np
 
 from tools.audio import float_to_int16, has_ffmpeg_installed
 from tools.logger import get_logger

examples/web/webui.py

@@ -155,6 +155,9 @@ def main():
                 streaming=stream,
                 interactive=False,
                 show_label=True,
+                waveform_options=gr.WaveformOptions(
+                    sample_rate=24000,
+                ),
             )
             generate_button.click(
                 fn=set_buttons_before_generate,

tools/audio/__init__.py

@@ -1,3 +1,3 @@
-from .mp3 import wav_arr_to_mp3_view
+from .pcm import pcm_arr_to_mp3_view
 from .ffmpeg import has_ffmpeg_installed
 from .np import float_to_int16

tools/audio/pcm.py

@@ -7,7 +7,7 @@ from .np import float_to_int16
 from .av import wav2
 
 
-def wav_arr_to_mp3_view(wav: np.ndarray):
+def pcm_arr_to_mp3_view(wav: np.ndarray):
     buf = BytesIO()
     with wave.open(buf, "wb") as wf:
         wf.setnchannels(1)  # Mono channel