Leaving AutoPlay Unchecked Produces Processing But 00:00 Output
Describe the bug If AutoPlay isn't checked, and Generate Speech is used, processing activity is seen in the logs (see below). However the displayed duration is 00:00, which makes it appear there's no output to be saved. In fact, a WAV or MP3 file can be saved, and it will contain well-formed data (i.e., correct speech). Additionally, clicking on "Play" produces no audible speech; "Generate Speech" must be used again, even though the text was processed.
Screenshots or console output
2025-03-18 10:57:34 2025-03-18 14:57:34.377 | INFO | __main__:download_model:60 - Model files already exist and are valid
2025-03-18 10:57:40 INFO: Started server process [30]
2025-03-18 10:57:40 INFO: Waiting for application startup.
2025-03-18 10:57:40 /app/.venv/lib/python3.10/site-packages/torch/nn/modules/rnn.py:123: UserWarning: dropout option adds dropout after all but last recurrent layer, so non-zero dropout expects num_layers greater than 1, but got dropout=0.2 and num_layers=1
2025-03-18 10:57:40 warnings.warn(
2025-03-18 10:57:40 /app/.venv/lib/python3.10/site-packages/torch/nn/utils/weight_norm.py:143: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.
2025-03-18 10:57:40 WeightNorm.apply(module, name, dim)
2025-03-18 10:57:43 INFO: Application startup complete.
2025-03-18 10:57:43 INFO: Uvicorn running on http://0.0.0.0:8880 (Press CTRL+C to quit)
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.28ms for chunk: 'With my written report in the watch log, I signed ...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.18ms for chunk: 'Chapter Thirty-five
2025-03-18 10:59:21 "You woke me up to tell me th...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.07ms for chunk: 'Think about it!'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.23ms for chunk: 'Sanders and Beale handled cattle which weren't the...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.20ms for chunk: 'The Knudsens did their work on cattle Sanders and ...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.09ms for chunk: 'Who's in the middle?'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.08ms for chunk: 'Sanders.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.35ms for chunk: '"Sanders, talking with other agents, can spot a pl...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.23ms for chunk: 'He sent Dolan, the Knudsens off to cut out however...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.26ms for chunk: 'The brands were changed along the way, and they ad...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.30ms for chunk: '"Beale got charged for the cattle—'Gotta buy grub ...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.24ms for chunk: 'Maybe Beale wasn't happy about it, but he must hav...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.35ms for chunk: 'All he did is graze them long enough to get them t...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.13ms for chunk: 'It's every rustler's story.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.10ms for chunk: 'Why'd you get me up at—Lord!'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.29ms for chunk: 'Is it really two in the mornin'?"
2025-03-18 10:59:21 "Sure it's an o...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.09ms for chunk: 'Forget the Knudsens;'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.43ms for chunk: 'they're just tools no different than a hay fork." ...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.07ms for chunk: 'But you not there yet.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.61ms for chunk: 'We need to know more 'bout what's going on between...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.25ms for chunk: 'Less cuts to Dolan an' the rest."
2025-03-18 10:59:21 Gus nodded.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.13ms for chunk: '"Could be right, but it's an old story:'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.11ms for chunk: 'takin' a shortcut to getting' rich.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.17ms for chunk: 'What you haven't told me is about Sanders and Dola...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.09ms for chunk: '"I don't have a sure answer.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.16ms for chunk: 'Sometimes I see Sanders holding the reins.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.09ms for chunk: ''Dolan, go to the XYZ.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.27ms for chunk: 'There's a hundred head you can drive to Beale's pl...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.18ms for chunk: ''Sanders, I can get a hold of a hundred head.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.17ms for chunk: 'Tell Beale he's gonna take them, and make sure I g...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.18ms for chunk: '"Funny thing is, I don't think either of them can ...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.12ms for chunk: 'They're pretty much tied together, like it or not.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.14ms for chunk: '"Dolan knows all about Sanders.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.31ms for chunk: 'If Sanders crosses Dolan, guess who can tell the w...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.13ms for chunk: 'Dolan has Sanders by the short hairs.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.18ms for chunk: 'The same's true for Sanders.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.21ms for chunk: 'He knows what Dolan's been up to.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.31ms for chunk: 'Sanders is holding Dolan by the short hairs."
2025-03-18 10:59:21 Gus...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.23ms for chunk: '"OK, Dolan's back trail's safe;'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.20ms for chunk: 'Sanders can't talk.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.45ms for chunk: 'But why does Dolan want anything more to do with S...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.17ms for chunk: 'Sanders is Dolan's quick way to find and sell catt...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.32ms for chunk: '"Thinking back to what Jesse said, I reckon Sander...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.13ms for chunk: 'This poor soul's gonna get used the way Beale was.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.17ms for chunk: 'Or he's too willin' to try for easy money."
2025-03-18 10:59:21 Gus n...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.10ms for chunk: '"You've got something.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.08ms for chunk: 'What you don't have is proof.'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.26ms for chunk: 'Nobody's tied Sanders, with solid proof, directly ...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.46ms for chunk: 'We haven't seen Sanders with cows marked by crooke...'
2025-03-18 10:59:21 02:59:21 PM | DEBUG | text_processor:51 | Total processing took 0.23ms for chunk: 'You're going to say something might have Sheriff G...'
2025-03-18 10:59:21 02:59:21 PM | INFO | text_processor:199 | Yielding chunk 1: 'Doctor James pronounced himself satisfied with Jes...' (259 tokens)
2025-03-18 10:59:21 02:59:21 PM | INFO | kokoro_v1:73 | Creating new pipeline for language code: b
2025-03-18 10:59:22 02:59:22 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Doctor James pronounced himself satisfied with Jesse Hoskins' progress. The bump I'd raised on his h...'
2025-03-18 10:59:22 02:59:22 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([353400])
2025-03-18 10:59:23 02:59:23 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([58200])
2025-03-18 10:59:23 02:59:23 PM | INFO | text_processor:199 | Yielding chunk 2: 'I'm hopin' t' get to Abilene, find some fellers he...' (225 tokens)
2025-03-18 10:59:23 02:59:23 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'I'm hopin' t' get to Abilene, find some fellers headin' back t' Texas, see if I can bunk over th' wi...'
2025-03-18 10:59:23 02:59:23 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([237600])
2025-03-18 10:59:23 02:59:23 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([124200])
2025-03-18 10:59:23 02:59:23 PM | INFO | text_processor:199 | Yielding chunk 3: '"
2025-03-18 10:59:23 "Huh?"
2025-03-18 10:59:23 "No whiskey."
2025-03-18 10:59:23 "Oh. That."
2025-03-18 10:59:23 "Leave whisk...' (236 tokens)
2025-03-18 10:59:23 02:59:23 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': '"
2025-03-18 10:59:23 "Huh?"
2025-03-18 10:59:23 "No whiskey."
2025-03-18 10:59:23 "Oh. That."
2025-03-18 10:59:23 "Leave whiskey alone for as long as you can stand. Beer should...'
2025-03-18 10:59:23 02:59:23 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([12000])
2025-03-18 10:59:23 02:59:23 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([32400])
2025-03-18 10:59:24 02:59:24 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([43200])
2025-03-18 10:59:24 02:59:24 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([39600])
2025-03-18 10:59:24 02:59:24 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([183000])
2025-03-18 10:59:24 02:59:24 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([136800])
2025-03-18 10:59:24 02:59:24 PM | INFO | text_processor:199 | Yielding chunk 4: 'Wouldn't do to be too deep into Sheriff Giddens ba...' (271 tokens)
2025-03-18 10:59:24 02:59:24 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Wouldn't do to be too deep into Sheriff Giddens bad books."
2025-03-18 10:59:24 I'd told Jesse the story of how I'd bec...'
2025-03-18 10:59:24 02:59:24 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([103800])
2025-03-18 10:59:25 02:59:25 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([312600])
2025-03-18 10:59:25 02:59:25 PM | INFO | text_processor:199 | Yielding chunk 5: 'Not the greatest place, but they ain't poisoned me...' (192 tokens)
2025-03-18 10:59:25 02:59:25 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Not the greatest place, but they ain't poisoned me yet. Watch your money, though."
2025-03-18 10:59:25 *
2025-03-18 10:59:25 It was three f...'
2025-03-18 10:59:25 02:59:25 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([129600])
2025-03-18 10:59:25 02:59:25 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([156000])
2025-03-18 10:59:25 02:59:25 PM | INFO | text_processor:199 | Yielding chunk 6: 'The enforced idleness had left Jesse with little c...' (228 tokens)
2025-03-18 10:59:25 02:59:25 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'The enforced idleness had left Jesse with little choice on how to pass the time except to talk with ...'
2025-03-18 10:59:25 02:59:25 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([346800])
2025-03-18 10:59:25 02:59:25 PM | INFO | text_processor:199 | Yielding chunk 7: 'In the Grande Palais, we just about bumped into ea...' (207 tokens)
2025-03-18 10:59:25 02:59:25 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'In the Grande Palais, we just about bumped into each other trying to find a free table. "Deputy Mall...'
2025-03-18 10:59:26 02:59:26 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([284400])
2025-03-18 10:59:26 02:59:26 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([43200])
2025-03-18 10:59:26 02:59:26 PM | INFO | text_processor:199 | Yielding chunk 8: '"If there was, Deputy Miller, people would see who...' (239 tokens)
2025-03-18 10:59:26 02:59:26 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': '"If there was, Deputy Miller, people would see who was in here, and the place would either be closed...'
2025-03-18 10:59:26 02:59:26 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([190800])
2025-03-18 10:59:26 02:59:26 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([93000])
2025-03-18 10:59:26 02:59:26 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([123000])
2025-03-18 10:59:26 02:59:26 PM | INFO | text_processor:199 | Yielding chunk 9: 'As she bent down to set the tray on the table, Gus...' (243 tokens)
2025-03-18 10:59:26 02:59:26 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'As she bent down to set the tray on the table, Gus and I started laughing after a quick look at Jess...'
2025-03-18 10:59:26 02:59:26 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([286200])
2025-03-18 10:59:27 02:59:27 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([112800])
2025-03-18 10:59:27 02:59:27 PM | INFO | text_processor:199 | Yielding chunk 10: 'What're ya laughin' at?"
2025-03-18 10:59:27 I looked at Gus. He look...' (178 tokens)
2025-03-18 10:59:27 02:59:27 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'What're ya laughin' at?"
2025-03-18 10:59:27 I looked at Gus. He looked at me. My turn to explain. "Well, you were look...'
2025-03-18 10:59:27 02:59:27 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([60600])
2025-03-18 10:59:27 02:59:27 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([215400])
2025-03-18 10:59:27 02:59:27 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([38400])
2025-03-18 10:59:27 02:59:27 PM | INFO | text_processor:199 | Yielding chunk 11: 'Bendin' over, showin' all that?"
2025-03-18 10:59:27 "We sho do mean ...' (230 tokens)
2025-03-18 10:59:27 02:59:27 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Bendin' over, showin' all that?"
2025-03-18 10:59:27 "We sho do mean Nan an' her Grand Canyon."
2025-03-18 10:59:27 "Grand Canyon, huh. Ai...'
2025-03-18 10:59:27 02:59:27 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([72000])
2025-03-18 10:59:27 02:59:27 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([89400])
2025-03-18 10:59:28 02:59:28 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([141600])
2025-03-18 10:59:28 02:59:28 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([104400])
2025-03-18 10:59:28 02:59:28 PM | INFO | text_processor:199 | Yielding chunk 12: 'You sho enough was lookin'. Like to fall in, you w...' (203 tokens)
2025-03-18 10:59:28 02:59:28 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'You sho enough was lookin'. Like to fall in, you was." The three of us chuckled, and dove into the s...'
2025-03-18 10:59:28 02:59:28 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([307800])
2025-03-18 10:59:28 02:59:28 PM | INFO | text_processor:199 | Yielding chunk 13: 'Patrolling the stockyards tonight, checking office...' (175 tokens)
2025-03-18 10:59:28 02:59:28 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Patrolling the stockyards tonight, checking offices and testing doors, would going to be cold going....'
2025-03-18 10:59:28 02:59:28 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([249600])
2025-03-18 10:59:28 02:59:28 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([35400])
2025-03-18 10:59:29 02:59:29 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([39600])
2025-03-18 10:59:29 02:59:29 PM | INFO | text_processor:199 | Yielding chunk 14: 'You said he had a kinda unpleasant Mick, name of D...' (206 tokens)
2025-03-18 10:59:29 02:59:29 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'You said he had a kinda unpleasant Mick, name of Donlan?"
2025-03-18 10:59:29 "Ike Dolan. I tried to stay wide of him. ...'
2025-03-18 10:59:29 02:59:29 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([102000])
2025-03-18 10:59:29 02:59:29 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([142200])
2025-03-18 10:59:29 02:59:29 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([99600])
2025-03-18 10:59:29 02:59:29 PM | INFO | text_processor:199 | Yielding chunk 15: 'Feller I'm minded of, heard someone say, 'some fol...' (211 tokens)
2025-03-18 10:59:29 02:59:29 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Feller I'm minded of, heard someone say, 'some folks call him "Ginger" on account'a his hair, an' je...'
2025-03-18 10:59:29 02:59:29 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([224400])
2025-03-18 10:59:29 02:59:29 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([97800])
2025-03-18 10:59:29 02:59:29 PM | INFO | text_processor:199 | Yielding chunk 16: '"Sounds about right."
2025-03-18 10:59:29 Out of the corner of my eye...' (192 tokens)
2025-03-18 10:59:29 02:59:29 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': '"Sounds about right."
2025-03-18 10:59:29 Out of the corner of my eye, I saw Gus set his mug down, sit slightly closer....'
2025-03-18 10:59:30 02:59:30 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([50400])
2025-03-18 10:59:30 02:59:30 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([253800])
2025-03-18 10:59:30 02:59:30 PM | INFO | text_processor:199 | Yielding chunk 17: 'Couldn't get prices worth spit, so we drove 'em he...' (234 tokens)
2025-03-18 10:59:30 02:59:30 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Couldn't get prices worth spit, so we drove 'em here."
2025-03-18 10:59:30 He chuckled. "Dunno why the boss thought Tex...'
2025-03-18 10:59:30 02:59:30 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([96000])
2025-03-18 10:59:30 02:59:30 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([274200])
2025-03-18 10:59:30 02:59:30 PM | INFO | text_processor:199 | Yielding chunk 18: 'Indian agent gave us a price worth only a little m...' (205 tokens)
2025-03-18 10:59:30 02:59:30 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Indian agent gave us a price worth only a little more'n hot spit. "Anyways, we picked up a new drove...'
2025-03-18 10:59:30 02:59:30 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([313200])
2025-03-18 10:59:31 02:59:31 PM | INFO | text_processor:199 | Yielding chunk 19: 'Head o' hair like he was on fire."
2025-03-18 10:59:31 "Sounds like R...' (242 tokens)
2025-03-18 10:59:31 02:59:31 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Head o' hair like he was on fire."
2025-03-18 10:59:31 "Sounds like Red Halloran. Kind of a gangly fella? Worked for me...'
2025-03-18 10:59:31 02:59:31 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([75600])
2025-03-18 10:59:31 02:59:31 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([192600])
2025-03-18 10:59:31 02:59:31 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([118200])
2025-03-18 10:59:31 02:59:31 PM | INFO | text_processor:199 | Yielding chunk 20: '"So Dolan sucker-punched Halloran? Huh. Explains t...' (231 tokens)
2025-03-18 10:59:31 02:59:31 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': '"So Dolan sucker-punched Halloran? Huh. Explains things, 'cause this fella sure had no time for Dola...'
2025-03-18 10:59:31 02:59:31 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([355800])
2025-03-18 10:59:31 02:59:31 PM | INFO | text_processor:199 | Yielding chunk 21: 'Said he'd worked out how he was goin' t' be forema...' (228 tokens)
2025-03-18 10:59:31 02:59:31 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Said he'd worked out how he was goin' t' be foreman at some spread, had a deal with some agent weren...'
2025-03-18 10:59:32 02:59:32 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([312600])
2025-03-18 10:59:32 02:59:32 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([30000])
2025-03-18 10:59:32 02:59:32 PM | INFO | text_processor:199 | Yielding chunk 22: 'Let me get this straight. Red Halloran came up fro...' (190 tokens)
2025-03-18 10:59:32 02:59:32 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Let me get this straight. Red Halloran came up from Abilene with you?"
2025-03-18 10:59:32 "Yep. Halloran for sure."
2025-03-18 10:59:32 "...'
2025-03-18 10:59:32 02:59:32 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([111600])
2025-03-18 10:59:32 02:59:32 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([60000])
2025-03-18 10:59:32 02:59:32 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([85200])
2025-03-18 10:59:32 02:59:32 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([34200])
2025-03-18 10:59:32 02:59:32 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([57600])
2025-03-18 10:59:33 02:59:33 PM | INFO | text_processor:199 | Yielding chunk 23: 'Jesse had just told us where Dolan had disappeared...' (240 tokens)
2025-03-18 10:59:33 02:59:33 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Jesse had just told us where Dolan had disappeared to. "Dolan was looking for a couple of boys who m...'
2025-03-18 10:59:33 02:59:33 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([315600])
2025-03-18 10:59:33 02:59:33 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([38400])
2025-03-18 10:59:33 02:59:33 PM | INFO | text_processor:199 | Yielding chunk 24: 'Jesse spoke emphatically. "Feller shows up at a Te...' (193 tokens)
2025-03-18 10:59:33 02:59:33 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Jesse spoke emphatically. "Feller shows up at a Texas spread, says, 'I'm gonna be your new foreman, ...'
2025-03-18 10:59:33 02:59:33 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([309000])
2025-03-18 10:59:33 02:59:33 PM | INFO | text_processor:199 | Yielding chunk 25: 'Now, if he was t' find a spread not doin' so good,...' (313 tokens)
2025-03-18 10:59:33 02:59:33 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Now, if he was t' find a spread not doin' so good, maybe the owner isn't quite straight up 'bout thi...'
2025-03-18 10:59:33 02:59:33 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([387600])
2025-03-18 10:59:34 02:59:34 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([62400])
2025-03-18 10:59:34 02:59:34 PM | INFO | text_processor:199 | Yielding chunk 26: '"How'd he hear what Dolan's up to? Workin' for me,...' (251 tokens)
2025-03-18 10:59:34 02:59:34 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': '"How'd he hear what Dolan's up to? Workin' for me, Halloran did a day's work for a day's wages. Stru...'
2025-03-18 10:59:34 02:59:34 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([218400])
2025-03-18 10:59:34 02:59:34 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([160800])
2025-03-18 10:59:34 02:59:34 PM | INFO | text_processor:199 | Yielding chunk 27: 'Place like that, feller lookin' t' find a couple h...' (183 tokens)
2025-03-18 10:59:34 02:59:34 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Place like that, feller lookin' t' find a couple hard case waddies, easy t' know he's askin' 'round....'
2025-03-18 10:59:34 02:59:34 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([179400])
2025-03-18 10:59:34 02:59:34 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([104400])
2025-03-18 10:59:34 02:59:34 PM | INFO | text_processor:224 | Yielding chunk 28: 'I hoped I sounded casual as I said, "makes sense."...' (160 tokens)
2025-03-18 10:59:34 02:59:34 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'I hoped I sounded casual as I said, "makes sense."
2025-03-18 10:59:34 With the last of my beer gone, I stood up. "Gent...'
2025-03-18 10:59:34 02:59:34 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([100800])
2025-03-18 10:59:35 02:59:35 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([166800])
2025-03-18 10:59:35 02:59:35 PM | INFO | text_processor:199 | Yielding chunk 29: 'Much as I'd like to stay, and hear how Texas' Palo...' (438 tokens)
2025-03-18 10:59:35 02:59:35 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Much as I'd like to stay, and hear how Texas' Palo Duro is better'n Nan's Grand Canyon, I've got to ...'
2025-03-18 10:59:35 02:59:35 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([186000])
2025-03-18 10:59:35 02:59:35 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([199200])
2025-03-18 10:59:36 02:59:36 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([153600])
2025-03-18 10:59:36 02:59:36 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([53400])
2025-03-18 10:59:36 02:59:36 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([123000])
2025-03-18 10:59:36 02:59:36 PM | INFO | text_processor:199 | Yielding chunk 30: 'Instead, after almost four months I knew where Ike...' (181 tokens)
2025-03-18 10:59:36 02:59:36 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Instead, after almost four months I knew where Ike Dolan had gone. If Dolan was looking for new wadd...'
2025-03-18 10:59:36 02:59:36 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([265800])
2025-03-18 10:59:36 02:59:36 PM | INFO | text_processor:199 | Yielding chunk 31: '"All" I had to do was figure out which person, whi...' (243 tokens)
2025-03-18 10:59:36 02:59:36 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': '"All" I had to do was figure out which person, which ranch Dolan was headed for. Wendell Sanders was...'
2025-03-18 10:59:36 02:59:36 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([362400])
2025-03-18 10:59:36 02:59:36 PM | INFO | text_processor:199 | Yielding chunk 32: 'No question Sanders could hide behind a corkscrew....' (226 tokens)
2025-03-18 10:59:36 02:59:36 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'No question Sanders could hide behind a corkscrew. He'd pestered the mayor into having someone from ...'
2025-03-18 10:59:37 02:59:37 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([330600])
2025-03-18 10:59:37 02:59:37 PM | INFO | text_processor:199 | Yielding chunk 33: 'The more I thought over what I'd heard, and what I...' (228 tokens)
2025-03-18 10:59:37 02:59:37 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'The more I thought over what I'd heard, and what I was sure about, the more I thought Sanders was al...'
2025-03-18 10:59:37 02:59:37 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([324600])
2025-03-18 10:59:37 02:59:37 PM | INFO | text_processor:199 | Yielding chunk 34: 'Things seemed to go from Dolan to Beale to Sanders...' (289 tokens)
2025-03-18 10:59:37 02:59:37 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Things seemed to go from Dolan to Beale to Sanders, but I didn't feel sure it was how things had wor...'
2025-03-18 10:59:37 02:59:37 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([168000])
2025-03-18 10:59:37 02:59:37 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([265800])
2025-03-18 10:59:37 02:59:37 PM | INFO | text_processor:199 | Yielding chunk 35: 'A wind gust occasionally kicked up dust, and ice s...' (208 tokens)
2025-03-18 10:59:37 02:59:37 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'A wind gust occasionally kicked up dust, and ice skins had begun to form in horse troughs. Put simpl...'
2025-03-18 10:59:38 02:59:38 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([326400])
2025-03-18 10:59:38 02:59:38 PM | INFO | text_processor:199 | Yielding chunk 36: 'I peered into windows, and tried doors. I carried ...' (218 tokens)
2025-03-18 10:59:38 02:59:38 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'I peered into windows, and tried doors. I carried a "Found Door Open" notice form, stating I'd found...'
2025-03-18 10:59:38 02:59:38 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([320400])
2025-03-18 10:59:38 02:59:38 PM | INFO | text_processor:199 | Yielding chunk 37: 'I was in the process of signing one of those notic...' (220 tokens)
2025-03-18 10:59:38 02:59:38 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'I was in the process of signing one of those notices when I figured out how to make Sanders a round ...'
2025-03-18 10:59:38 02:59:38 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([330600])
2025-03-18 10:59:38 02:59:38 PM | INFO | text_processor:199 | Yielding chunk 38: 'Inside, I lit the lamp on the first desk I came to...' (246 tokens)
2025-03-18 10:59:38 02:59:38 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Inside, I lit the lamp on the first desk I came to. Tengvald Brothers, Cattle Agents' office looked ...'
2025-03-18 10:59:38 02:59:38 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([385200])
2025-03-18 10:59:38 02:59:38 PM | INFO | text_processor:199 | Yielding chunk 39: 'The ledger pages showed accounts of cattle receive...' (211 tokens)
2025-03-18 10:59:38 02:59:38 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'The ledger pages showed accounts of cattle received, age, condition, price, and, of course, the ear ...'
2025-03-18 10:59:39 02:59:39 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([336000])
2025-03-18 10:59:39 02:59:39 PM | INFO | text_processor:199 | Yielding chunk 40: 'Following common practice, one ranch's herd had be...' (248 tokens)
2025-03-18 10:59:39 02:59:39 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Following common practice, one ranch's herd had been part of a drive moving several ranches' herds. ...'
2025-03-18 10:59:39 02:59:39 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([378600])
2025-03-18 10:59:39 02:59:39 PM | INFO | text_processor:199 | Yielding chunk 41: 'A ranch using the brand Rafter Over RW had done al...' (360 tokens)
2025-03-18 10:59:39 02:59:39 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'A ranch using the brand Rafter Over RW had done alright with their cattle. A herd of 1157 cattle, re...'
2025-03-18 10:59:39 02:59:39 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([491400])
2025-03-18 10:59:39 02:59:39 PM | INFO | text_processor:199 | Yielding chunk 42: 'Get back to work, Miller, and stop staring at not ...' (281 tokens)
2025-03-18 10:59:39 02:59:39 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Get back to work, Miller, and stop staring at not your business. I got out the "Found Door Open" not...'
2025-03-18 10:59:40 02:59:40 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([410400])
2025-03-18 10:59:40 02:59:40 PM | INFO | text_processor:199 | Yielding chunk 43: 'The road brand was simple: Box Circle Dot, a squar...' (265 tokens)
2025-03-18 10:59:40 02:59:40 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'The road brand was simple: Box Circle Dot, a square with a circle centered inside it, and a dot cent...'
2025-03-18 10:59:40 02:59:40 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([411600])
2025-03-18 10:59:40 02:59:40 PM | INFO | text_processor:199 | Yielding chunk 44: 'I've never been buffaloed. But, looking at the roa...' (309 tokens)
2025-03-18 10:59:40 02:59:40 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'I've never been buffaloed. But, looking at the road brand, I felt as though I'd been buffaloed. It w...'
2025-03-18 10:59:40 02:59:40 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([439200])
2025-03-18 10:59:40 02:59:40 PM | INFO | text_processor:199 | Yielding chunk 45: 'Dolan and his men either rustled cattle, or took o...' (175 tokens)
2025-03-18 10:59:40 02:59:40 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Dolan and his men either rustled cattle, or took on cattle Sanders found for Dolan. Dolan's boss, or...'
2025-03-18 10:59:40 02:59:40 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([279600])
2025-03-18 10:59:40 02:59:40 PM | INFO | text_processor:199 | Yielding chunk 46: 'Came time to drive the cattle to market, they were...' (211 tokens)
2025-03-18 10:59:40 02:59:40 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Came time to drive the cattle to market, they were sold at market prices, making a big profit in the...'
2025-03-18 10:59:41 02:59:41 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([314400])
2025-03-18 10:59:41 02:59:41 PM | INFO | text_processor:199 | Yielding chunk 47: 'You damn sure didn't pay for these cattle."
2025-03-18 10:59:41 "Maybe...' (259 tokens)
2025-03-18 10:59:41 02:59:41 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'You damn sure didn't pay for these cattle."
2025-03-18 10:59:41 "Maybe not, but we didn't get 'em here for nothin', neit...'
2025-03-18 10:59:41 02:59:41 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([79800])
2025-03-18 10:59:41 02:59:41 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([193800])
2025-03-18 10:59:41 02:59:41 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([79800])
2025-03-18 10:59:41 02:59:41 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([72600])
2025-03-18 10:59:41 02:59:41 PM | INFO | text_processor:199 | Yielding chunk 48: 'Stop actin' like y'are."
2025-03-18 10:59:41 Deputy Alread, to my gre...' (273 tokens)
2025-03-18 10:59:41 02:59:41 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Stop actin' like y'are."
2025-03-18 10:59:41 Deputy Alread, to my great thanks, arrived early at the watch office. I to...'
2025-03-18 10:59:41 02:59:41 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([58200])
2025-03-18 10:59:42 02:59:42 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([364200])
2025-03-18 10:59:42 02:59:42 PM | INFO | text_processor:199 | Yielding chunk 49: 'Places with stoves or fires looked safe enough. Wi...' (240 tokens)
2025-03-18 10:59:42 02:59:42 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Places with stoves or fires looked safe enough. With my written report in the watch log, I signed my...'
2025-03-18 10:59:42 02:59:42 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([285000])
2025-03-18 10:59:42 02:59:42 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([60600])
2025-03-18 10:59:42 02:59:42 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([52200])
2025-03-18 10:59:42 02:59:42 PM | INFO | text_processor:199 | Yielding chunk 50: 'Sanders and Beale handled cattle which weren't the...' (190 tokens)
2025-03-18 10:59:42 02:59:42 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Sanders and Beale handled cattle which weren't theirs, but cooked things to look like they were. The...'
2025-03-18 10:59:42 02:59:42 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([293400])
2025-03-18 10:59:42 02:59:42 PM | INFO | text_processor:199 | Yielding chunk 51: '"Sanders, talking with other agents, can spot a pl...' (231 tokens)
2025-03-18 10:59:42 02:59:42 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': '"Sanders, talking with other agents, can spot a place where it might be easy to run off enough cattl...'
2025-03-18 10:59:43 02:59:43 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([333000])
2025-03-18 10:59:43 02:59:43 PM | INFO | text_processor:199 | Yielding chunk 52: 'The brands were changed along the way, and they ad...' (214 tokens)
2025-03-18 10:59:43 02:59:43 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'The brands were changed along the way, and they added a road brand to make the drive look believable...'
2025-03-18 10:59:43 02:59:43 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([329400])
2025-03-18 10:59:43 02:59:43 PM | INFO | text_processor:199 | Yielding chunk 53: 'Maybe Beale wasn't happy about it, but he must hav...' (286 tokens)
2025-03-18 10:59:43 02:59:43 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Maybe Beale wasn't happy about it, but he must have known he wasn't out the cost of raising cattle f...'
2025-03-18 10:59:43 02:59:43 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([371400])
2025-03-18 10:59:43 02:59:43 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([31800])
2025-03-18 10:59:43 02:59:43 PM | INFO | text_processor:199 | Yielding chunk 54: 'It's every rustler's story. Why'd you get me up at...' (204 tokens)
2025-03-18 10:59:43 02:59:43 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'It's every rustler's story. Why'd you get me up at—Lord! Is it really two in the mornin'?"
2025-03-18 10:59:43 "Sure it...'
2025-03-18 10:59:43 02:59:43 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([152400])
2025-03-18 10:59:44 02:59:44 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([180000])
2025-03-18 10:59:44 02:59:44 PM | INFO | text_processor:199 | Yielding chunk 55: 'they're just tools no different than a hay fork." ...' (201 tokens)
2025-03-18 10:59:44 02:59:44 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'they're just tools no different than a hay fork."
2025-03-18 10:59:44 Gus stretched, yawned, and said, "alright, grante...'
2025-03-18 10:59:44 02:59:44 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([88800])
2025-03-18 10:59:44 02:59:44 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([227400])
2025-03-18 10:59:44 02:59:44 PM | INFO | text_processor:199 | Yielding chunk 56: 'We need to know more 'bout what's going on between...' (265 tokens)
2025-03-18 10:59:44 02:59:44 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'We need to know more 'bout what's going on between Dolan and Sanders."
2025-03-18 10:59:44 "All I know for sure is Beal...'
2025-03-18 10:59:44 02:59:44 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([116400])
2025-03-18 10:59:44 02:59:44 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([263400])
2025-03-18 10:59:44 02:59:44 PM | INFO | text_processor:199 | Yielding chunk 57: 'Less cuts to Dolan an' the rest."
2025-03-18 10:59:44 Gus nodded. "Co...' (224 tokens)
2025-03-18 10:59:44 02:59:44 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Less cuts to Dolan an' the rest."
2025-03-18 10:59:44 Gus nodded. "Could be right, but it's an old story: takin' a shor...'
2025-03-18 10:59:45 02:59:45 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([72000])
2025-03-18 10:59:45 02:59:45 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([229800])
2025-03-18 10:59:45 02:59:45 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([77400])
2025-03-18 10:59:45 02:59:45 PM | INFO | text_processor:199 | Yielding chunk 58: 'Sometimes I see Sanders holding the reins. 'Dolan,...' (223 tokens)
2025-03-18 10:59:45 02:59:45 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Sometimes I see Sanders holding the reins. 'Dolan, go to the XYZ. There's a hundred head you can dri...'
2025-03-18 10:59:45 02:59:45 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([355800])
2025-03-18 10:59:45 02:59:45 PM | INFO | text_processor:199 | Yielding chunk 59: 'Tell Beale he's gonna take them, and make sure I g...' (218 tokens)
2025-03-18 10:59:45 02:59:45 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Tell Beale he's gonna take them, and make sure I get my cut of his money for those cattle'. "Funny t...'
2025-03-18 10:59:45 02:59:45 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([321000])
2025-03-18 10:59:45 02:59:45 PM | INFO | text_processor:199 | Yielding chunk 60: '"Dolan knows all about Sanders. If Sanders crosses...' (234 tokens)
2025-03-18 10:59:45 02:59:45 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': '"Dolan knows all about Sanders. If Sanders crosses Dolan, guess who can tell the world what Wendell ...'
2025-03-18 10:59:46 02:59:46 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([363600])
2025-03-18 10:59:46 02:59:46 PM | INFO | text_processor:199 | Yielding chunk 61: 'Sanders is holding Dolan by the short hairs."
2025-03-18 10:59:46 Gus...' (303 tokens)
2025-03-18 10:59:46 02:59:46 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Sanders is holding Dolan by the short hairs."
2025-03-18 10:59:46 Gus nodded. "OK, Dolan's back trail's safe; Sanders c...'
2025-03-18 10:59:46 02:59:46 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([91200])
2025-03-18 10:59:46 02:59:46 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([222600])
2025-03-18 10:59:46 02:59:46 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([187200])
2025-03-18 10:59:46 02:59:46 PM | INFO | text_processor:199 | Yielding chunk 62: 'Sanders is Dolan's quick way to find and sell catt...' (248 tokens)
2025-03-18 10:59:46 02:59:46 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Sanders is Dolan's quick way to find and sell cattle. "Thinking back to what Jesse said, I reckon Sa...'
2025-03-18 10:59:46 02:59:46 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([388200])
2025-03-18 10:59:47 02:59:47 PM | INFO | text_processor:199 | Yielding chunk 63: 'Or he's too willin' to try for easy money."
2025-03-18 10:59:47 Gus n...' (198 tokens)
2025-03-18 10:59:47 02:59:47 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'Or he's too willin' to try for easy money."
2025-03-18 10:59:47 Gus nodded. "You've got something. What you don't have ...'
2025-03-18 10:59:47 02:59:47 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([84000])
2025-03-18 10:59:47 02:59:47 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([223200])
2025-03-18 10:59:47 02:59:47 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([37200])
2025-03-18 10:59:47 02:59:47 PM | INFO | text_processor:199 | Yielding chunk 64: 'We haven't seen Sanders with cows marked by crooke...' (190 tokens)
2025-03-18 10:59:47 02:59:47 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'We haven't seen Sanders with cows marked by crooked brands we can tie to him, I'm just darn sure it ...'
2025-03-18 10:59:47 02:59:47 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([177000])
2025-03-18 10:59:47 02:59:47 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([127800])
2025-03-18 10:59:47 02:59:47 PM | INFO | text_processor:236 | Yielding final chunk 65: 'You're going to say something might have Sheriff G...' (80 tokens)
2025-03-18 10:59:47 02:59:47 PM | DEBUG | kokoro_v1:244 | Generating audio for text with lang_code 'b': 'You're going to say something might have Sheriff Giddens unhappy with you, aren't you?"'
2025-03-18 10:59:48 02:59:48 PM | DEBUG | kokoro_v1:251 | Got audio chunk with shape: torch.Size([122400])
2025-03-18 10:59:48 02:59:48 PM | INFO | text_processor:242 | Split completed in 26494.14ms, produced 65 chunks
Branch / Deployment used Generated with docker run --gpus all -p 127.0.0.1:8880:8880 ghcr.io/remsky/kokoro-fastapi-gpu:latest on 2025-03-18 14:30:42 EDT.
Operating System Docker 4.39.0, Win 11 on i9, RTX4090 16 Gb VRAM, 64 Gb RAM
Additional context Situation is repeatable at will.
I have the same problem but even with Auto play enabled. It worked in a test container a few days ago but now it wont. Tested on Edge and Brave Borwser 138.0.3351.95 on two different PCs. Can't explain why that is all of a sudden.
05:56:37 PM | DEBUG | paths:153 | Scanning for voices in path: /app/api/src/voices/v1_0 05:56:37 PM | DEBUG | streaming_audio_writer:40 | Disabling Xing VBR header for MP3 encoding. INFO: 172.27.72.1:64592 - "POST /v1/audio/speech HTTP/1.1" 200 OK 05:56:37 PM | DEBUG | paths:153 | Scanning for voices in path: /app/api/src/voices/v1_0 05:56:37 PM | DEBUG | paths:131 | Searching for voice in path: /app/api/src/voices/v1_0 05:56:37 PM | DEBUG | tts_service:204 | Using single voice path: /app/api/src/voices/v1_0/af_alloy.pt 05:56:37 PM | DEBUG | tts_service:280 | Using voice path: /app/api/src/voices/v1_0/af_alloy.pt 05:56:37 PM | INFO | tts_service:284 | Using lang_code 'a' for voice 'af_alloy' in audio stream 05:56:37 PM | INFO | text_processor:159 | Starting smart split for 349 chars 05:56:37 PM | DEBUG | text_processor:164 | Split raw text into 1 parts by pause tags. 05:56:37 PM | DEBUG | text_processor:65 | Total processing took 0.57ms for chunk: 'Tomato plants are vines, largely annual and vulner...' 05:56:37 PM | DEBUG | text_processor:65 | Total processing took 0.19ms for chunk: 'The flowers are able to self-fertilise.' 05:56:37 PM | DEBUG | text_processor:65 | Total processing took 0.46ms for chunk: 'Modern varieties have been bred to ripen uniformly...' 05:56:37 PM | DEBUG | text_processor:65 | Total processing took 0.39ms for chunk: 'There are thousands of cultivars, varying in size,...' 05:56:37 PM | INFO | text_processor:271 | Yielding chunk 1: 'Tomato plants are vines, largely annual and vulner...' (291 tokens) 05:56:37 PM | DEBUG | kokoro_v1:261 | Generating audio for text with lang_code 'a': 'Tomato plants are vines, largely annual and vulnerable to frost, though sometimes living longer in g...' 05:56:37 PM | DEBUG | kokoro_v1:268 | Got audio chunk with shape: torch.Size([378000]) 05:56:37 PM | INFO | text_processor:308 | Yielding final chunk 2 for part: 'There are thousands of cultivars, varying in size,...' (79 tokens) 05:56:37 PM | DEBUG | kokoro_v1:261 | Generating audio for text with lang_code 'a': 'There are thousands of cultivars, varying in size, color, shape, and flavor.' 05:56:38 PM | DEBUG | kokoro_v1:268 | Got audio chunk with shape: torch.Size([122400]) 05:56:38 PM | INFO | text_processor:332 | Split completed in 1059.01ms, produced 2 chunks (including pauses) 05:56:38 PM | DEBUG | streaming_audio_writer:85 | Muxed final packets.
Operating System Docker version 28.3.2, build 578ccf6, Debian 12.11 on GTX 1070 TI 8Gb VRAM