expand numbers, new examples.

app.py

@@ -33,9 +33,15 @@ gr.Interface(
     fn=speak,
     inputs="text",
     examples=[
-        "this is a test!",
+        "This is a test!",
+        "President Trump met with other leaders at the Group of 20 conference.",
+        "The buses aren't the problem, they actually provide a solution.",
+        "Generative adversarial network or variational auto-encoder.",
+        "Basilar membrane and otolaryngology are not auto-correlations.",
+        "There are several variations on the full gated unit, with gating done using the previous hidden state and the bias in various combinations, and a simplified form called minimal gated unit.",
         "October arrived, spreading a damp chill over the grounds and into the castle. Madam Pomfrey, the nurse, was kept busy by a sudden spate of colds among the staff and students.",
         "Artificial intelligence is intelligence demonstrated by machines, as opposed to natural intelligence displayed by animals including humans.",
+        'Uncle Vernon entered the kitchen as Harry was turning over the bacon. "Comb your hair!" he barked, by way of a morning greeting. About once a week, Uncle Vernon looked over the top of his newspaper and shouted that Harry needed a haircut. Harry must have had more haircuts than the rest of the boys in his class put together, but it made no difference, his hair simply grew that way - all over the place.',
     ],
     outputs="audio",
     title=title,

inference.py

@@ -28,7 +28,7 @@ def load_tacotron_model(alphabet_file, config_file, model_file):
     return alphabet, net, config
 
 
-tacotron_inference_fn = pax.pure(lambda net, text: net.inference(text, max_len=500))
+tacotron_inference_fn = pax.pure(lambda net, text: net.inference(text, max_len=1200))
 
 
 def text_to_mel(net, text, alphabet, config):

mynumbers.py

@@ -0,0 +1,73 @@
+""" from https://github.com/keithito/tacotron """
+
+import inflect
+import re
+
+
+_inflect = inflect.engine()
+_comma_number_re = re.compile(r"([0-9][0-9\,]+[0-9])")
+_decimal_number_re = re.compile(r"([0-9]+\.[0-9]+)")
+_pounds_re = re.compile(r"£([0-9\,]*[0-9]+)")
+_dollars_re = re.compile(r"\$([0-9\.\,]*[0-9]+)")
+_ordinal_re = re.compile(r"[0-9]+(st|nd|rd|th)")
+_number_re = re.compile(r"[0-9]+")
+
+
+def _remove_commas(m):
+    return m.group(1).replace(",", "")
+
+
+def _expand_decimal_point(m):
+    return m.group(1).replace(".", " point ")
+
+
+def _expand_dollars(m):
+    match = m.group(1)
+    parts = match.split(".")
+    if len(parts) > 2:
+        return match + " dollars"  # Unexpected format
+    dollars = int(parts[0]) if parts[0] else 0
+    cents = int(parts[1]) if len(parts) > 1 and parts[1] else 0
+    if dollars and cents:
+        dollar_unit = "dollar" if dollars == 1 else "dollars"
+        cent_unit = "cent" if cents == 1 else "cents"
+        return "%s %s, %s %s" % (dollars, dollar_unit, cents, cent_unit)
+    elif dollars:
+        dollar_unit = "dollar" if dollars == 1 else "dollars"
+        return "%s %s" % (dollars, dollar_unit)
+    elif cents:
+        cent_unit = "cent" if cents == 1 else "cents"
+        return "%s %s" % (cents, cent_unit)
+    else:
+        return "zero dollars"
+
+
+def _expand_ordinal(m):
+    return _inflect.number_to_words(m.group(0))
+
+
+def _expand_number(m):
+    num = int(m.group(0))
+    if num > 1000 and num < 3000:
+        if num == 2000:
+            return "two thousand"
+        elif num > 2000 and num < 2010:
+            return "two thousand " + _inflect.number_to_words(num % 100)
+        elif num % 100 == 0:
+            return _inflect.number_to_words(num // 100) + " hundred"
+        else:
+            return _inflect.number_to_words(
+                num, andword="", zero="oh", group=2
+            ).replace(", ", " ")
+    else:
+        return _inflect.number_to_words(num, andword="")
+
+
+def normalize_numbers(text):
+    text = re.sub(_comma_number_re, _remove_commas, text)
+    text = re.sub(_pounds_re, r"\1 pounds", text)
+    text = re.sub(_dollars_re, _expand_dollars, text)
+    text = re.sub(_decimal_number_re, _expand_decimal_point, text)
+    text = re.sub(_ordinal_re, _expand_ordinal, text)
+    text = re.sub(_number_re, _expand_number, text)
+    return text

requirements.txt

@@ -1,10 +1,11 @@
+gradio
+inflect==5.4.0
 jax==0.3.1
 jaxlib==0.3.0
-numpy==1.22.3
+jinja2
 librosa==0.9.1
+numpy==1.22.3
 pax3==0.5.6
-gradio
-jinja2
+pyyaml==6.0
 toml==0.10.2
-unidecode==1.3.4
-pyyaml==6.0
+unidecode==1.3.4

text.py

@@ -13,7 +13,7 @@ hyperparameter. Some cleaners are English-specific. You'll typically want to use
 """
 
 import re
-
+from mynumbers import normalize_numbers
 from unidecode import unidecode
 
 # Regular expression matching whitespace:
@@ -51,6 +51,10 @@ def expand_abbreviations(text):
     return text
 
 
+def expand_numbers(text):
+    return normalize_numbers(text)
+
+
 def lowercase(text):
     return text.lower()
 
@@ -82,6 +86,7 @@ def english_cleaners(text):
     """Pipeline for English text, including number and abbreviation expansion."""
     text = convert_to_ascii(text)
     text = lowercase(text)
+    text = expand_numbers(text)
     text = expand_abbreviations(text)
     text = collapse_whitespace(text)
     return text

wavegru.ckpt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64b1ce6558cfe09b95bb29d48c34900ed0c3490d17c81fd6190969b226f4617a
+oid sha256:377de02cc88587e3562bdc709d48a43d00c901198d6b018bf6e1734211036577
 size 58039876