ar+nar-len-llama-8
Model (
ar+nar
)

This is from a snapshot of the weights post-training for NAR-len modality, but outputs from the original AR+NAR modality.
Average WER: 0.240
Average CER: 0.146
Average SIM-O: 0.873

LibriSpeech
Text WER↓ CER↓ SIM-O↑ Prompt Our VALL-E Original VALL-E Ground Truth
Number ten, fresh nelly is waiting on you, good night husband. 0.1820.0320.668
Yea, his honourable worship is within, but he hath a godly minister or two with him, and likewise a leech. 0.1500.0450.945
Instead of shoes, the old man wore boots with turnover tops, and his blue coat had wide cuffs of gold braid. 0.0480.0090.852
The army found the people in poverty and left them in comparative wealth. 0.3080.1450.930
Thus did this humane and right minded father comfort his unhappy daughter, and her mother embracing her again, did all she could to soothe her feelings. 0.5000.2880.824
He was in deep converse with the clerk and entered the hall holding him by the arm. 0.0000.0000.906
They moved thereafter cautiously about the hut groping before and about them to find something to show that Warrenton had fulfilled his mission. 0.2170.0850.832
And lay me down in thy cold bed and leave my shining lot. 0.8460.6720.789
Sampled Dataset
Text WER↓ CER↓ SIM-O↑ Prompt Our VALL-E Ground Truth
I can't tell you how glad I am to have you so pretty and comfortable here, and to hear everyone saying such nice things about you. 0.0000.0000.980
The other is a mythological subject of deeper meaning, the death of Procrus. 0.0770.0630.945
And yet, that something must be playful in its nature. 0.1000.0190.949
Each day has its own great gree for its little care. 0.0910.0530.898
It seems to be easier than it is, I begin to think, replied Philip. 0.0000.0000.883
He rode before a portmanteau and called himself Ashburnham's servant. 0.2000.0680.852
Unless you speak more fully senora, I cannot understand you. replied her husband. 0.0770.0230.867
It did not beckon, or indeed move at all. It was as still as the hand of death. 0.8240.6670.770
Lafe and grim shall be the same kind of friends to your two sons. 0.1430.0870.848
real dishonor consistent sin, and real honor in virtue. 1.1110.6290.863
On the palm were three little pyramids of black, doughy clay. 1.0000.8810.906
Most people talk too much, so it is a relief to find one who talks too little. 0.0000.0000.863
One evening there came a sudden flash of fire and a sputtering, sizzling noise. 0.2860.1050.902
Well, you are sad every day. 0.0000.0000.691
This invidious traditional distinction has not lost its force even among the more advanced people of today. 0.1250.0450.953
That's a poor saying," said Amiel, stooping over to wipe his hands in the wet grass. 0.0670.0370.930
If I must say it, Mother, I want to go away and get out of this dead level. 0.1760.1590.883
Don't know, most everything she says sounds like the Bible or Shakespeare to me. 0.0000.0000.953
He worked me very hard. He wanted to be beating me all the time. 0.0000.0000.844
I gave her a spray of lilac. I remember and you gave her a friend. 0.0000.0000.918
He was handsome and bold and pleasant, offhand and gay and kind. 0.1670.0590.969
If I had only seen her, I should have declared it to be a vision, but I spoke to her. 0.0000.0000.891
The Count advanced a step towards his friend and pressed him warmly in his arms. 0.0670.0120.781
I just touched something soft. On the instant Joyce was at her side with a candle. 0.7330.5540.719
The story won't tell," said Douglas, not in any literal vulgar way. 0.0000.0000.918
Why don't you do flowers and houses, Olive? inquired serosalicitously. 0.4000.1070.887
There it clothed itself in word masks, in metaphor rags. 0.4000.2410.863
The stars began to crumble and a cloud of fine stardust fell through space. 0.2860.0630.820
Among the exhibits of that exposition was the Edison system of incandescent lighting. 0.0000.0000.902
What did old mom be the witch do with the powder of life your husband gave her? Ask the boy. 0.6320.5860.828
apathy and disgust commonly follows satiated lust. 0.2860.0350.973
She, however, did not bestow a single glance upon him. 0.1110.0700.910

Settings used:

{'task': 'tts', 'modality': 'ar+nar', 'max_steps': 50, 'max_levels': 7, 'max_duration': 900, 'ar_temperature': 0.95, 'nar_temperature': 0.0, 'min_ar_temperature': -1.0, 'min_nar_temperature': -1.0, 'top_p': 1.0, 'top_k': 0, 'top_no': 0.0, 'min_p': 0.0, 'repetition_penalty': 1.0, 'repetition_penalty_decay': 0.0, 'length_penalty': 0.0, 'beam_width': 0, 'mirostat_tau': 0, 'mirostat_eta': 0, 'dry_multiplier': 0, 'dry_base': 1.75, 'dry_allowed_length': 2, 'input_prompt_length': 0.0, 'input_prompt_prefix': False, 'prefix_silence': 0.0, 'cfg_strength': 1.0, 'cfg_rescale': 0.75, 'seed': 1733980473, 'tqdm': True, 'batch_size': 4}