Update kokoro.py

kokoro.py

@@ -1,7 +1,15 @@
-import phonemizer
 import re
 import torch
 import numpy as np
+from gtts import gTTS  # Import gTTS for text-to-speech
+
+# Replace phonemizer backend with gTTS
+def phonemize_with_gtts(text, lang='en'):
+    tts = gTTS(text=text, lang=lang)
+    # gTTS does not return phonemes, so we will simply return the text itself
+    # In your original code, this is where phonemizing is used
+    # For now, we can return the text or adapt further as needed
+    return text
 
 def split_num(num):
     num = num.group()
@@ -84,19 +92,19 @@ def get_vocab():
     return dicts
 
 VOCAB = get_vocab()
+
 def tokenize(ps):
     return [i for i in map(VOCAB.get, ps) if i is not None]
 
 phonemizers = dict(
-    a=phonemizer.backend.EspeakBackend(language='en-us', preserve_punctuation=True, with_stress=True),
-    b=phonemizer.backend.EspeakBackend(language='en-gb', preserve_punctuation=True, with_stress=True),
+    a=phonemize_with_gtts,  # Replace with the new phonemizer function
+    b=phonemize_with_gtts,  # Same for other language options
 )
+
 def phonemize(text, lang, norm=True):
     if norm:
         text = normalize_text(text)
-    ps = phonemizers[lang].phonemize([text])
-    ps = ps[0] if ps else ''
-    # https://en.wiktionary.org/wiki/kokoro#English
+    ps = phonemizers[lang](text)
     ps = ps.replace('kəkˈoːɹoʊ', 'kˈoʊkəɹoʊ').replace('kəkˈɔːɹəʊ', 'kˈəʊkəɹəʊ')
     ps = ps.replace('ʲ', 'j').replace('r', 'ɹ').replace('x', 'k').replace('ɬ', 'l')
     ps = re.sub(r'(?<=[a-zɹː])(?=hˈʌndɹɪd)', ' ', ps)
@@ -118,48 +126,4 @@ def forward(model, tokens, ref_s, speed):
     input_lengths = torch.LongTensor([tokens.shape[-1]]).to(device)
     text_mask = length_to_mask(input_lengths).to(device)
     bert_dur = model.bert(tokens, attention_mask=(~text_mask).int())
-    d_en = model.bert_encoder(bert_dur).transpose(-1, -2)
-    s = ref_s[:, 128:]
-    d = model.predictor.text_encoder(d_en, s, input_lengths, text_mask)
-    x, _ = model.predictor.lstm(d)
-    duration = model.predictor.duration_proj(x)
-    duration = torch.sigmoid(duration).sum(axis=-1) / speed
-    pred_dur = torch.round(duration).clamp(min=1).long()
-    pred_aln_trg = torch.zeros(input_lengths, pred_dur.sum().item())
-    c_frame = 0
-    for i in range(pred_aln_trg.size(0)):
-        pred_aln_trg[i, c_frame:c_frame + pred_dur[0,i].item()] = 1
-        c_frame += pred_dur[0,i].item()
-    en = d.transpose(-1, -2) @ pred_aln_trg.unsqueeze(0).to(device)
-    F0_pred, N_pred = model.predictor.F0Ntrain(en, s)
-    t_en = model.text_encoder(tokens, input_lengths, text_mask)
-    asr = t_en @ pred_aln_trg.unsqueeze(0).to(device)
-    return model.decoder(asr, F0_pred, N_pred, ref_s[:, :128]).squeeze().cpu().numpy()
-
-def generate(model, text, voicepack, lang='a', speed=1, ps=None):
-    ps = ps or phonemize(text, lang)
-    tokens = tokenize(ps)
-    if not tokens:
-        return None
-    elif len(tokens) > 510:
-        tokens = tokens[:510]
-        print('Truncated to 510 tokens')
-    ref_s = voicepack[len(tokens)]
-    out = forward(model, tokens, ref_s, speed)
-    ps = ''.join(next(k for k, v in VOCAB.items() if i == v) for i in tokens)
-    return out, ps
-
-def generate_full(model, text, voicepack, lang='a', speed=1, ps=None):
-    ps = ps or phonemize(text, lang)
-    tokens = tokenize(ps)
-    if not tokens:
-        return None
-    outs = []
-    loop_count = len(tokens)//510 + (1 if len(tokens) % 510 != 0 else 0)
-    for i in range(loop_count):
-        ref_s = voicepack[len(tokens[i*510:(i+1)*510])]
-        out = forward(model, tokens[i*510:(i+1)*510], ref_s, speed)
-        outs.append(out)
-    outs = np.concatenate(outs)
-    ps = ''.join(next(k for k, v in VOCAB.items() if i == v) for i in tokens)
-    return outs, ps
+    d_en = model.bert_encoder(bert_dur).transpose(-1, -2