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

This is from a snapshot of the weights post-Emilia post-training, but before training for the NAR-len modality.
Average WER: 0.138
Average CER: 0.062
Average SIM-O: 0.905

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. 0.1820.0320.742
Yea, his honourable worship is within, but he hath a godly minister or two with him, and likewise a leech. 0.1500.0730.977
Instead of shoes, the old man wore boots with turnover tops, and his blue coat had wide cuffs of gold braid. 0.0000.0000.895
The army found the people in poverty and left them in comparative wealth. 0.1540.0790.938
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. 0.2310.0780.914
He was in deep converse with the clerk and entered the hall holding him by the arm. 0.0000.0000.926
They moved thereafter cautiously about the hut groping before and about them to find something to show that Warrenton had fulfilled his mission. 0.3910.1760.898
And lay me down in thy cold bed and leave my shining lot. 0.1540.0900.801
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. 0.0000.0000.926
The other is a mythological subject of deeper meaning, the death of Procrus. 0.2310.2150.945
And yet, that something must be playful in its nature. 0.1000.0370.961
Each day has its own great gree for its little care. 0.1820.1050.945
It seems to be easier than it is, I begin to think, replied Philip. 0.0000.0000.949
He rode before a portmanteau and called himself Ashburnham's servant. 0.4000.1780.863
Unless you speak more fully senora, I cannot understand you. replied her husband. 0.1540.0340.930
It did not beckon, or indeed move at all. It was as still as the hand of death. 0.2940.2470.852
Lafe and grim shall be the same kind of friends to your two sons. 0.1430.0430.895
real dishonor consistent sin, and real honor in virtue. 1.0000.3060.805
On the palm were three little pyramids of black, doughy clay. 0.1000.0170.902
Most people talk too much, so it is a relief to find one who talks too little. 0.0000.0000.941
One evening there came a sudden flash of fire and a sputtering, sizzling noise. 0.0000.0000.906
Well, you are sad every day. 0.0000.0000.887
This invidious traditional distinction has not lost its force even among the more advanced people of today. 0.1880.0630.941
That's a poor saying," said Amiel, stooping over to wipe his hands in the wet grass. 0.0670.0250.922
If I must say it, Mother, I want to go away and get out of this dead level. 0.0000.0000.914
Don't know, most everything she says sounds like the Bible or Shakespeare to me. 0.0000.0000.930
He worked me very hard. He wanted to be beating me all the time. 0.0000.0000.883
I gave her a spray of lilac. I remember and you gave her a friend. 0.0000.0000.926
He was handsome and bold and pleasant, offhand and gay and kind. 0.0000.0000.977
If I had only seen her, I should have declared it to be a vision, but I spoke to her. 0.0000.0000.934
The Count advanced a step towards his friend and pressed him warmly in his arms. 0.0000.0000.824
I just touched something soft. On the instant Joyce was at her side with a candle. 0.1330.0840.883
The story won't tell," said Douglas, not in any literal vulgar way. 0.0830.0290.820
Why don't you do flowers and houses, Olive? inquired serosalicitously. 0.3000.1730.898
There it clothed itself in word masks, in metaphor rags. 0.4000.1720.922
The stars began to crumble and a cloud of fine stardust fell through space. 0.1430.0760.863
Among the exhibits of that exposition was the Edison system of incandescent lighting. 0.0000.0000.910
What did old mom be the witch do with the powder of life your husband gave her? Ask the boy. 0.2110.1410.949
apathy and disgust commonly follows satiated lust. 0.1430.0180.980
She, however, did not bestow a single glance upon him. 0.0000.0000.918

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': 1733980651, 'tqdm': True, 'batch_size': 4}