Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,21 +1,27 @@
|
|
| 1 |
import spaces
|
| 2 |
-
import os
|
| 3 |
-
import sys
|
| 4 |
sys.path.append("neutts-air")
|
| 5 |
from neuttsair.neutts import NeuTTSAir
|
| 6 |
import numpy as np
|
| 7 |
import gradio as gr
|
| 8 |
|
|
|
|
| 9 |
SAMPLES_PATH = os.path.join(os.getcwd(), "neutts-air", "samples")
|
| 10 |
DEFAULT_REF_TEXT = "So I'm live on radio. And I say, well, my dear friend James here clearly, and the whole room just froze. Turns out I'd completely misspoken and mentioned our other friend."
|
| 11 |
DEFAULT_REF_PATH = os.path.join(SAMPLES_PATH, "dave.wav")
|
| 12 |
DEFAULT_GEN_TEXT = "My name is Dave, and um, I'm from London."
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
tts = NeuTTSAir(
|
| 15 |
backbone_repo="neuphonic/neutts-air",
|
| 16 |
-
backbone_device="
|
| 17 |
codec_repo="neuphonic/neucodec",
|
| 18 |
-
codec_device="
|
| 19 |
)
|
| 20 |
|
| 21 |
@spaces.GPU()
|
|
@@ -35,6 +41,7 @@ def infer(
|
|
| 35 |
tuple [int, np.ndarray]: A tuple containing the sample rate (24000) and the generated audio waveform as a numpy array.
|
| 36 |
"""
|
| 37 |
|
|
|
|
| 38 |
gr.Info("Starting inference request!")
|
| 39 |
gr.Info("Encoding reference...")
|
| 40 |
ref_codes = tts.encode_reference(ref_audio_path)
|
|
|
|
| 1 |
import spaces
|
| 2 |
+
import os, sys, logging
|
|
|
|
| 3 |
sys.path.append("neutts-air")
|
| 4 |
from neuttsair.neutts import NeuTTSAir
|
| 5 |
import numpy as np
|
| 6 |
import gradio as gr
|
| 7 |
|
| 8 |
+
|
| 9 |
SAMPLES_PATH = os.path.join(os.getcwd(), "neutts-air", "samples")
|
| 10 |
DEFAULT_REF_TEXT = "So I'm live on radio. And I say, well, my dear friend James here clearly, and the whole room just froze. Turns out I'd completely misspoken and mentioned our other friend."
|
| 11 |
DEFAULT_REF_PATH = os.path.join(SAMPLES_PATH, "dave.wav")
|
| 12 |
DEFAULT_GEN_TEXT = "My name is Dave, and um, I'm from London."
|
| 13 |
|
| 14 |
+
logging.basicConfig(
|
| 15 |
+
level=logging.INFO,
|
| 16 |
+
format="%(asctime)s [%(levelname)s] %(message)s",
|
| 17 |
+
stream=sys.stdout
|
| 18 |
+
)
|
| 19 |
+
|
| 20 |
tts = NeuTTSAir(
|
| 21 |
backbone_repo="neuphonic/neutts-air",
|
| 22 |
+
backbone_device="cpu",
|
| 23 |
codec_repo="neuphonic/neucodec",
|
| 24 |
+
codec_device="cpu"
|
| 25 |
)
|
| 26 |
|
| 27 |
@spaces.GPU()
|
|
|
|
| 41 |
tuple [int, np.ndarray]: A tuple containing the sample rate (24000) and the generated audio waveform as a numpy array.
|
| 42 |
"""
|
| 43 |
|
| 44 |
+
logging.info(f"Using reference: {ref_audio_path}")
|
| 45 |
gr.Info("Starting inference request!")
|
| 46 |
gr.Info("Encoding reference...")
|
| 47 |
ref_codes = tts.encode_reference(ref_audio_path)
|