Below are some samples from my VALL-E implementation: https://git.ecker.tech/mrq/vall-e/.
Unlike the original VALL-E demo page, I'm placing emphasis on the input prompt, as the model adheres to it stronger than others.
Objective metrics are computed by transcribing (openai/whisper-base) then comparing the word error rate on transcriptions (WER/CER), and computing the cosine similarities on embeddings through a speaker feature extraction model (microsoft/wavlm-base-sv) (SIM-O) between the output audio and the prompt.
Tables marked as "Validation" are samples not seen to the model.
Other model demo pages: [ar+nar-len-llama-8 (ar+nar)] [ar+nar-len-llama-8 (nar-len)] [ar+nar-llama-8 (ar+nar)] | Old demo pages: [1] [2] [3]
ar+nar-len-llama-8Model (
nar-len)
Average WER: 0.067
Average CER: 0.020
Average SIM-O: 0.891
| 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. | 0.182 | 0.032 | 0.781 | ||||
| Yea, his honourable worship is within, but he hath a godly minister or two with him, and likewise a leech. | 0.000 | 0.000 | 0.961 | ||||
| Instead of shoes, the old man wore boots with turnover tops, and his blue coat had wide cuffs of gold braid. | 0.143 | 0.051 | 0.914 | ||||
| The army found the people in poverty and left them in comparative wealth. | 0.000 | 0.000 | 0.879 | ||||
| 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. | 0.077 | 0.013 | 0.770 | ||||
| He was in deep converse with the clerk and entered the hall holding him by the arm. | 0.000 | 0.000 | 0.922 | ||||
| They moved thereafter cautiously about the hut groping before and about them to find something to show that Warrenton had fulfilled his mission. | 0.261 | 0.106 | 0.750 | ||||
| And lay me down in thy cold bed and leave my shining lot. | 0.077 | 0.045 | 0.887 |
| Text | WER↓ | CER↓ | SIM-O↑ | Prompt | Our VALL-E | Ground Truth |
|---|---|---|---|---|---|---|
| If any boys have special confessors, perhaps it will be better for them not to change. | 0.000 | 0.000 | 0.836 | |||
| It can't be for money or balls or play and he has no honest business anywhere. | 0.000 | 0.000 | 0.953 | |||
| How long are we likely to be separated? Why are we to be denied each other's society? | 0.067 | 0.055 | 0.906 | |||
| Unless you speak more fully senora, I cannot understand you. replied her husband. | 0.231 | 0.045 | 0.805 | |||
| What did it avail to pray when he knew that his soul lusted after its own destruction? | 0.000 | 0.000 | 0.867 | |||
| You may wonder to hear me speak thus, being so young. | 0.091 | 0.035 | 0.906 | |||
| Here, he proceeded to swallow his prize head first. | 0.000 | 0.000 | 0.898 | |||
| Happily for him, he, on his part, caught sight of the hawk and dropped like lead into the point. | 0.111 | 0.071 | 0.809 | |||
| Put them away quick before Andela and Rosalie see them. | 0.200 | 0.033 | 0.965 | |||
| Humble man that he was, he will not now take a back seat. | 0.154 | 0.032 | 0.965 | |||
| We lay there, our blood running cold with unspeakable terror. | 0.000 | 0.000 | 0.965 | |||
| Irene Vergoyne, one of her family, told me in confidence that there was a romance somewhere back in the beginning. | 0.000 | 0.000 | 0.965 | |||
| I like trees because they seem more resigned to the way they have to live than other things do. | 0.000 | 0.000 | 0.887 | |||
| You are mad. She has given birth to a princess. | 0.000 | 0.000 | 0.957 | |||
| They sat down side by side and Dorcas held her hand. | 0.182 | 0.051 | 0.879 | |||
| The Latter-day Saints were long regarded as a polygamous people. | 0.200 | 0.030 | 0.879 | |||
| Stop it, said Buttonbright. I can't hear myself think. | 0.222 | 0.035 | 0.871 | |||
| But look here, at Carpaccio, even in my copy. | 0.000 | 0.000 | 0.859 | |||
| A sudden wave of scarlets swept over Eliza's face. | 0.111 | 0.018 | 0.961 | |||
| No, I am quite proud of my person, was the reply. | 0.000 | 0.000 | 0.902 | |||
| I telephoned again and felt something would happen, but fortunately it did not. | 0.000 | 0.000 | 0.879 | |||
| A veiled sunlight lit up faintly the gray sheet of water where the river was embayed. | 0.000 | 0.000 | 0.887 | |||
| The wind was flapping her big hat and teasing a curl of her chestnut-colored hair. | 0.000 | 0.000 | 0.961 | |||
| Then the curtain rises and it is apparent that we are assisting at an at-home of considerable splendor. | 0.222 | 0.078 | 0.910 | |||
| I want to be something, to make myself something, to do something. | 0.000 | 0.000 | 0.922 | |||
| No, it was not their colors. It was the poise and balance of the period itself. | 0.000 | 0.000 | 0.898 | |||
| Dearest, Teach me so to pour out gratitude, As thou dost good. | 0.000 | 0.000 | 0.906 | |||
| Burbank and his tribe represent in the vegetable world Edison in the mechanical | 0.000 | 0.000 | 0.934 | |||
| Very soon after dinner, Charles Smith excused himself. | 0.000 | 0.000 | 0.723 | |||
| Well then, I must make some suggestions to you. | 0.000 | 0.000 | 0.906 | |||
| It won't be much, but I'm grateful to find a friend. I'm guilty, you know, and there's no one to blame but myself. | 0.136 | 0.051 | 0.902 | |||
| She then rose, humming the air to which she was presently going to dance. | 0.000 | 0.000 | 0.930 |
Average WER: 0.061
Average CER: 0.027
Average SIM-O: 0.848
| Text | WER↓ | CER↓ | SIM-O↑ | Prompt | Our VALL-E | Ground Truth |
|---|---|---|---|---|---|---|
| Had a really good identity card, national identity card system. | 0.000 | 0.000 | 0.703 | |||
| Web on desktop has seen path breaking innovation in the last few years. | 0.000 | 0.000 | 0.668 | |||
| Quite prevalent here, here in Alberta and a lot of people just don't see it. | 0.000 | 0.000 | 0.797 | |||
| Hence, integrated pest management in cotton was a subject matter chosen for the Farm Field School | 0.000 | 0.000 | 0.648 | |||
| Or more importantly, some people may naturally heal over time. | 0.000 | 0.000 | 0.688 | |||
| Man, this is a fresh, something's happening. Something is stirring. | 0.100 | 0.158 | 0.848 | |||
| Depending like justice and aging and the AARP and the. | 0.500 | 0.143 | 0.957 | |||
| The peer to peer aspect of Bitcoin is not in the people, it's in the computers. | 0.214 | 0.103 | 0.848 | |||
| Very, very critical in how it actually plays a role in so many different ways. We need for you. | 0.000 | 0.000 | 0.871 | |||
| Tuesday, Thursday, and Saturday. Like space out the day, use if that makes sense. | 0.071 | 0.024 | 0.777 | |||
| Because the statute says whenever an allegation is raised, basically. | 0.000 | 0.000 | 0.895 | |||
| They gave us a list and I think I'm gonna go with something called direct relief. | 0.125 | 0.071 | 0.789 | |||
| Making resolution you need, and the composition automatically adjust to it. | 0.091 | 0.013 | 0.840 | |||
| State I won't read that comment. So before I start my command, | 0.000 | 0.000 | 0.832 | |||
| Best of all, they are a low cost, simple solution. | 0.000 | 0.000 | 0.926 | |||
| == Departments and programs == | 0.000 | 0.000 | 0.906 | |||
| During the Renaissance, the Age of Reason, and the Enlightenment, categorizing organisms became more prevalent | 0.000 | 0.000 | 0.930 | |||
| We've divided the project as a whole into three work streams. | 0.000 | 0.000 | 0.902 | |||
| Newton's laws of motion and Newton's law of universal gravitation were formulated in the 17th century | 0.067 | 0.033 | 0.977 | |||
| Due to fire suppression, forests have replaced many areas of former oak woodland | 0.000 | 0.000 | 0.957 | |||
| To equip young people with the tools needed to lead healthy and productive lives. | 0.000 | 0.000 | 0.898 | |||
| Because we didn't anticipate at the time of the original consent. | 0.000 | 0.000 | 0.824 | |||
| Before you, uh, as you're putting your screws in, okay? And then you're, you're gonna be all good there. | 0.053 | 0.031 | 0.906 | |||
| Since we are going long, we set our stop loss at the green ATR moving average. | 0.000 | 0.000 | 0.844 | |||
| Academic journals publish collections of articles throughout the year. | 0.000 | 0.000 | 0.914 | |||
| London 2012-2012 Microsoft Windows, PlayStation 3, Xbox 360 | 0.000 | 0.000 | 0.977 | |||
| Once we've calculated the number out required for our job, we can use that value to calculate the total number of sheets needed. | 0.130 | 0.074 | 0.934 | |||
| Satellite Pay TV is offered by the Wenanchi Group | 0.111 | 0.053 | 0.660 | |||
| I was just thinking, uhm, back in undergrad I learned about so many different... | 0.071 | 0.060 | 0.961 | |||
| A rear-facing television was mounted in the roof just behind | 0.000 | 0.000 | 0.648 | |||
| Uh, but this work also incorporates a significant portion on gender. | 0.091 | 0.039 | 0.785 | |||
| Cardinal Flavio began work on the Villa Chiga Versalia at Fermello in 1664 | 0.062 | 0.016 | 0.957 |
Average WER: 0.774
Average CER: 0.532
Average SIM-O: 0.895
| Text | WER↓ | CER↓ | SIM-O↑ | Prompt | Our VALL-E | Ground Truth |
|---|---|---|---|---|---|---|
| Car on joue de rencontre un team avec la personne du Saint-Esprit, où le Saint-Esprit l'a instruit. | 0.647 | 0.356 | 0.633 | |||
| La course à pied, ce n'est pas vraiment mon sport préféré. | 0.000 | 0.000 | 0.891 | |||
| Notre maison de rêve est là. | 0.500 | 0.308 | 0.895 | |||
| Voilà. Tu, tu archives. Ensuite, tu fais un making of. | 20.500 | 15.603 | 0.887 | |||
| Il ne faut pas croire cependant que tous les mormons soient polygammes. | 0.167 | 0.066 | 0.957 | |||
| Il lui faut trente heures pour faire le tour de Mars. | 0.273 | 0.163 | 0.934 | |||
| Il répondit, je n'ai été envoyé qu'au brebis perdu de la maison d'Israël, hein. | 0.429 | 0.228 | 0.727 | |||
| Cette belle fille | 0.667 | 0.846 | 0.887 | |||
| Le troisième besoin, c'est le besoin de rapports sociaux avec les autres êtres humains. | 0.143 | 0.059 | 0.914 | |||
| Oui, j'en ai pas mal. Avez-vous du temps maintenant ? | 0.000 | 0.000 | 0.961 | |||
| Comme vous l'a expliqué Patrick, euh, une des volontés. | 0.667 | 0.447 | 0.914 | |||
| Il se levait très tôt et venait tous les matins dans sa chambre. | 0.000 | 0.000 | 0.973 | |||
| C'est vraiment le cœur du système qu'on va changer et c'est très compliqué. | 0.077 | 0.014 | 0.844 | |||
| cet engrais vert doit également me permettre, au-delà de nourrir mon sol, il doit permettre de... | 0.438 | 0.146 | 0.922 | |||
| Parce que voilà, euh, c'est vrai que des fois, ça peut être un peu épuisant de donner, donner, donner, mais en fait, je sais pas faire autrement. | 0.346 | 0.175 | 0.965 | |||
| Ça me paraît, je veux pas, j'ai pas de boule de cristal et je suis pas expert en l'occurrence devant la justice. | 0.182 | 0.103 | 0.898 | |||
| euh, si vous voulez une version un petit peu plus difficile, vous montez. | 0.462 | 0.254 | 0.906 | |||
| Voilà. Et si, toi, tu n'exerces pas la miséricorde dans la droide? Ton frère. | 0.643 | 0.274 | 0.891 | |||
| C'est lui qui a l'ennite ou pas? C'est malheureusement moi. | 0.300 | 0.100 | 0.898 | |||
| être debout être debout | 0.000 | 0.000 | 0.922 | |||
| Et la nuit, en sasser dehors et en parler durant des heures. | 0.167 | 0.093 | 0.965 | |||
| Bastien a trois yeux. | 0.500 | 0.143 | 0.895 | |||
| Donc, euh, qu'il y a des gens qui savent très bien trader et qui vous donnent des bons conseils. Donc. | 0.250 | 0.212 | 0.945 | |||
| de s'en extraire, ou en tout cas de, de questionner cette violence ou de la mettre à distance. | 0.111 | 0.069 | 0.938 | |||
| Il y a juste une petite mani, donc, si ça reste un fichier SPSS, vous allez voir un fichier .dat. | 0.250 | 0.152 | 0.922 | |||
| euh, cet argent ne servira qu'à l'achat de matériel ou aux frais de déplacement de cas échéant. | 0.235 | 0.078 | 0.910 | |||
| Voilà, euh, c'est un peu psychos, hein. Un spot, ok. | 0.400 | 0.236 | 0.914 | |||
| Mais les grandes maisons de luxe n'existent pas encore. | 0.000 | 0.000 | 0.875 | |||
| l'organisation générale des Antiquités, des manuscrits et des musées, apparue dans les années 1970. | 0.312 | 0.064 | 0.922 | |||
| Et dans ces, cette époque-là, c'était, euh, il recommandait des livres de développement personnel. | 0.571 | 0.380 | 0.973 | |||
| L'eau aide à l'élimination des toxines et protège le foie contre le développement des calculs billaires. | 0.562 | 0.253 | 0.965 | |||
| Ouais, qui base. Alors, autant, on l'a vu au tout début, hein. RDF, il n'y en a qu'un. Type. | 0.421 | 0.195 | 0.891 |
Average WER: 0.252
Average CER: 0.121
Average SIM-O: 0.896
| Text | WER↓ | CER↓ | SIM-O↑ | Prompt | Our VALL-E | Ground Truth |
|---|---|---|---|---|---|---|
| Und das ist noch lange nicht alles. Es kommt noch viel schlimmer. | 0.000 | 0.000 | 0.969 | |||
| Ja mega, Ruhe. Bitte vermeiden Sie Lärm. | 0.286 | 0.067 | 0.812 | |||
| Und ich schlage vor, dass wir Getränke einkaufen. | 0.000 | 0.000 | 0.934 | |||
| Und die Reparatur hat viel Geld gekostet. | 0.000 | 0.000 | 0.918 | |||
| Die seinerzeit zu den Borschen des Dorfes gehört hatten, hießen nun Altbauern. | 0.250 | 0.047 | 0.941 | |||
| Ich habe ihn vorhin vor dem Kurs gesehen. Ich denke er wird gleich kommen. Ah, da ist er ja. | 0.158 | 0.050 | 0.934 | |||
| Das heißt, ich komme auch nicht wieder weg und kann holen gehen. Kann ich auf die schießen, Junge? | 0.000 | 0.000 | 0.910 | |||
| Aber sie zeigt mir, wie unbedeutend viele Dinge sind und dass ich mir keine Sorgen machen muss. | 0.059 | 0.030 | 0.953 | |||
| Machen wir weiter mit dem Präteritum. | 0.333 | 0.227 | 0.816 | |||
| Dort erwartete mich die Stuvades mit verwehrtem Gesicht. | 0.500 | 0.150 | 0.965 | |||
| Wo willst du denn grillen? Auf deinem Balkon? | 0.000 | 0.000 | 0.918 | |||
| Gut, dann auf Seite 94 haben wir einen. | 0.222 | 0.017 | 0.871 | |||
| Ach, Frau Meyer, guten Tag. Nein, ich wohne nicht hier. Wie geht es Ihnen? | 0.143 | 0.117 | 0.926 | |||
| Uh, wenn wir gegessen haben werden, werden wir schwimmen gehen. | 0.200 | 0.076 | 0.852 | |||
| Ja, das war, das war ein interessanter zu... | 0.250 | 0.196 | 0.895 | |||
| Gott ist für mich selber sehr vieles, aber die Wahrheit ist eins der... | 0.077 | 0.099 | 0.750 | |||
| Am Morgen nach der Party befindet sich Eddy in der Abstellkammer. | 0.182 | 0.189 | 0.961 | |||
| Die Straßenbahn. Die Straßenbahn. | 0.750 | 0.543 | 0.715 | |||
| Sie brauchen ihn wie die Mami. Täglich als Helfer bei den Schularbeiten. | 0.083 | 0.013 | 0.891 | |||
| Er kommt aus Nigeria. | 1.000 | 0.630 | 0.926 | |||
| Klar, aber jetzt fahren wir erst einmal in die Berge. | 0.200 | 0.143 | 0.895 | |||
| Es war einmal eine Kröte mit Warzen. | 0.286 | 0.045 | 0.840 | |||
| Damit ist das Wandern die absolute Nummer 1. | 0.125 | 0.059 | 0.918 | |||
| Nein, das ist von Joyce Carol Oates aus einem Essay über Boxen. | 0.500 | 0.329 | 0.871 | |||
| Martha spielt gut Gitarre. | 0.250 | 0.100 | 0.906 | |||
| Ich hab gemerkt, das hab ich letztens erst rausgekriegt, dass ich diesen Schiebebalken zwischen | 0.286 | 0.188 | 0.832 | |||
| Aus die, wegen der Kreuzungen und aus diversen Gründen. | 0.333 | 0.115 | 0.895 | |||
| Sobald es was zu berichten gibt, melden wir uns. Danke für eure anhaltende Unterstützung, eure Piranhas. | 0.188 | 0.067 | 0.949 | |||
| Im Moment geht ihr beide ja noch zur Schule und wohnt mit eurer Familie zusammen. | 0.133 | 0.022 | 0.887 | |||
| Erlassen wir dabei. Jo. Schön, Manuel. War eine nette Unterhaltung heute mit dir. | 0.385 | 0.193 | 0.977 | |||
| Euren WhatsApp-Verlauf interpretiert ihr sicher nicht im deutschen Unterricht, oder? | 0.100 | 0.073 | 0.926 | |||
| Auf ein Girokonto. Das Girokonto. | 0.800 | 0.098 | 0.930 |
Average WER: 1.182
Average CER: 0.198
Average SIM-O: 0.939
| Text | WER↓ | CER↓ | SIM-O↑ | Prompt | Our VALL-E | Ground Truth |
|---|---|---|---|---|---|---|
| 他にも動画がありますので、ぜひご覧ください。 | 0.000 | 0.000 | 0.918 | |||
| あ、そっちか。ね、ここは、今、セルバーさんに、 | 1.000 | 0.022 | 0.820 | |||
| 今年の大切なものについて紹介したいと思います。 | 1.000 | 0.722 | 0.973 | |||
| じゃあ決まったらこの紙に書いて持ってきます。 | 1.000 | 0.130 | 0.949 | |||
| 隣の部屋、10時までに片付けて下さい。 | 0.333 | 0.092 | 0.934 | |||
| 自動車の修理会社の人からメッセージが入っています。 | 0.722 | 0.599 | 0.953 | |||
| おとうさん | 0.000 | 0.000 | 0.930 | |||
| さて、今月も皆さんから頂いたお便りを紹介しようと思います。 | 2.000 | 0.181 | 0.980 | |||
| この魚は生では食べられないから、煮るなり焼くなりしてください。 | 2.000 | 0.023 | 0.949 | |||
| ただ、費用がかなりかかるから、新聞ってのはね。 | 1.000 | 0.288 | 0.918 | |||
| できている、完璧に、というふうに思っています。 | 2.000 | 0.033 | 0.918 | |||
| そうよ、うちのうえのこは。 | 0.000 | 0.000 | 0.918 | |||
| トコの部分に、あの、土入ってないとね、根っこ腐って枯れちゃう。 | 3.000 | 0.282 | 0.938 | |||
| はい。えっと、最近は、えっと、人間失格。 | 1.000 | 0.326 | 0.781 | |||
| あ、ちょっと待ってください。私は、 | 0.000 | 0.000 | 0.961 | |||
| ミニバンだからと言って、もうセッタカな車だからと言って、 | 2.000 | 0.043 | 0.930 | |||
| すみません。赤いボールペンありませんか? | 2.000 | 0.261 | 0.984 | |||
| で、これ、なんで赤くするのかっていうのはですね、え、赤色っていうのは目の刺激が少ないんですよ。 | 2.000 | 0.346 | 0.945 | |||
| 全く頼りにならない国のままだという印象を与えてしまうのではないでしょうか。 | 2.000 | 0.065 | 0.953 | |||
| 会社によっては、間の平日も休みにしたり、 | 0.000 | 0.000 | 0.965 | |||
| 私の国のカレーです。あまり辛くないですよ。 | 1.000 | 0.179 | 0.953 | |||
| ついに新しいクロップトップを切ることができます。 | 2.000 | 0.162 | 0.953 | |||
| 俺も職員の一人として一緒にくっついていくんだ。 | 1.000 | 0.169 | 0.949 | |||
| 問題が難しすぎるんじゃないですか? | 1.000 | 0.058 | 0.941 | |||
| ね、あの基本的にその自動調理器は一回スイッチ入れたら途中で、 | 5.000 | 0.489 | 0.969 | |||
| ヘアピンク感というか少しこうタイトなコーナーなんですけれども、すごく車が | 1.000 | 0.224 | 0.883 | |||
| 彼は一目で彼女を大好きになってしまった。 | 0.000 | 0.000 | 0.973 | |||
| 諸外国に比べて日本は食料品 が高いと言われている | 1.000 | 0.393 | 0.953 | |||
| 手元に届くまで2日しかかからなかったし送料も無料でしたし | 1.000 | 0.343 | 0.973 | |||
| お父さん、洋服はもうあまり着ないから。 | 0.000 | 0.000 | 0.977 | |||
| 大事なのは毒を盛る方法が他にあったかどうか。 | 1.000 | 0.127 | 0.930 | |||
| 手触りの良いコットンのトートバッグが入ってまして、 | 0.767 | 0.771 | 0.977 |
Average WER: 0.273
Average CER: 0.082
Average SIM-O: 0.921
| Text | WER↓ | CER↓ | SIM-O↑ | Prompt | Our VALL-E | Ground Truth |
|---|---|---|---|---|---|---|
| 부해의 법도 그 힘이 미치지 못합니다. | 0.250 | 0.041 | 0.902 | |||
| 이 기념 아시겠어요? 그래서 콜렉터와 어그리게이터는 굉장히 다른 겁니다. | 0.111 | 0.010 | 0.934 | |||
| 일본 활동 중 가장 추억에 남는 일은? | 0.000 | 0.000 | 0.926 | |||
| 도토리목 부추전, 도토리목 탕수육. 도토리목 빼렸는데 더 늘었네. | 0.000 | 0.000 | 0.945 | |||
| 11과 사과 5개 주세요. | 0.000 | 0.000 | 0.922 | |||
| 저리 가, 못생긴 늑대야! 내 집에는 절대 들어올 수 없을 거야! | 0.250 | 0.037 | 0.930 | |||
| 시골지는 음식을 먹을 생각에 매우 신이 났죠. | 0.000 | 0.000 | 0.832 | |||
| 뭐든 많이 하면 좋잖아요. | 1.000 | 0.194 | 0.957 | |||
| 그러다 보니까 아날로그틱한 액션신들을 좀 많이 넣어서 이제 | 0.500 | 0.114 | 0.941 | |||
| 그리고 보증금은 적으면 적을수록 좋습니다. | 0.000 | 0.000 | 0.980 | |||
| 두 번째 세트는 어떻게 진행될 것인지 잠시 후 양 팀의 2세트로 돌아오겠습니다. | 0.000 | 0.000 | 0.730 | |||
| 남녀노소 누구나 좋아하는 영양식으로 인기를 끌고 있습니다. | 0.400 | 0.026 | 0.945 | |||
| 우리 아기를 구한되다가 아직도 이렇게 훌륭하다는 걸 증명하는구나. | 0.000 | 0.000 | 0.883 | |||
| 아, 그래요? 회사에서 일본어가 필요해요? | 0.000 | 0.000 | 0.852 | |||
| 내일 비가 오지 않는다면 피크닉을 가질 거예요. | 0.000 | 0.000 | 0.895 | |||
| 상상할 수 없는 나쁜 놈이잖아요. 정말 인류 역사 속에 이렇게 나쁜 놈이 있을 수가 있겠어요? | 0.182 | 0.057 | 0.926 | |||
| 주말에 친구들과 같이 놀이공원에 가려고 해요. | 0.000 | 0.000 | 0.977 | |||
| 네, 이상 강연을 마치도록 하겠습니다. 셰프 김소봉이었습니다. 감사합니다. | 0.000 | 0.000 | 0.926 | |||
| 영진씨, 그래서 고속도로를 비롯한 모든 도로 및 철도가 | 0.333 | 0.092 | 0.949 | |||
| 어, 뭐라고, 뭐라고. | 1.000 | 0.550 | 0.855 | |||
| 오늘도 그 말씀과 동행하다가 주님 만나시기를 바랍니다. | 0.400 | 0.133 | 0.934 | |||
| 아, 이쪽은 이제 저거를 해와야 되는 거구나. 뭐지, 어떻게 하지? | 0.000 | 0.000 | 0.910 | |||
| 물을 많이 마시고 훅 쉬세요. | 0.500 | 0.061 | 0.953 | |||
| 지금 제가 일식 요리를 하게 된 바로 그 원동력입니다. | 0.222 | 0.068 | 0.938 | |||
| 화면으로 보이는 것와 같이 대면 교육을 진행합니다. | 0.286 | 0.056 | 0.953 | |||
| 읽으려고, 아, 읽으려고 도서관에 갔어요. | 0.400 | 0.083 | 0.949 | |||
| 아, 제목 어렵다. 뭐라고 하지? 숨 막히는 순간? 댓글에 그럴 것 같은데, 진짜 숨 막히는 영상이네요. | 0.154 | 0.015 | 0.961 | |||
| 음, 약간 냉팔보채 느낌? | 2.000 | 0.500 | 0.934 | |||
| 적어서 아직 말을 잘 못해요. | 0.000 | 0.000 | 0.938 | |||
| 여행가는 가까이 다가가서 더 자세히 관찰했어요. | 0.000 | 0.000 | 0.934 | |||
| 63빌딩이라고 들어봤어요. | 0.000 | 0.000 | 0.945 | |||
| 記者, 린다이, 메고 있어요. | 0.750 | 0.574 | 0.922 |
Average WER: 0.117
Average CER: 0.055
Average SIM-O: 0.898
| Text | WER↓ | CER↓ | SIM-O↑ | Prompt | Our VALL-E | Ground Truth |
|---|---|---|---|---|---|---|
| 嗯,还行,天霸混进去一个,嗯,灵树好像混进去。 | 0.278 | 0.123 | 0.977 | |||
| 工作人员以为他在开玩笑,便也故作一本正经的说。 | 0.000 | 0.000 | 0.945 | |||
| 这张啊名字叫难以忘怀的老师。 | 0.077 | 0.049 | 0.836 | |||
| 吃羊脸儿去把咱们饭店最好的羊脸拿上来。 | 0.056 | 0.043 | 0.934 | |||
| 咱们冒兴为这个密点，死的人还少吗？ | 0.067 | 0.011 | 0.723 | |||
| 好再来community刚才说community的交流，那们在同一个社区的全体居民或叫社区。 | 0.071 | 0.042 | 0.938 | |||
| 快递个we搞撒拉好，然后老我再放，你抢给我个time. | 0.350 | 0.200 | 0.914 | |||
| 刚才打开的那个保险库的门啊,然后这边可以看一下一些日志。 | 0.038 | 0.025 | 0.898 | |||
| 哦，那么快，这个家伙给我发了四十个。 | 0.133 | 0.022 | 0.957 | |||
| 常哥没关系，就算了吧，你就帮乐言打个架。 | 0.118 | 0.019 | 0.922 | |||
| 这是什么呢?是一场已经发生了改变的年代。 | 0.000 | 0.000 | 0.930 | |||
| 这个里面是周楠和一个叫东东的女孩的照片。 | 0.000 | 0.000 | 0.934 | |||
| 送你八字真年得之我幸失之我命。 | 0.214 | 0.045 | 0.820 | |||
| 我跟他说，让他假装你女朋友。 | 0.000 | 0.000 | 0.898 | |||
| 在导读当中我提到,它是我们十一章当中最重要的一个章节。 | 0.040 | 0.006 | 0.953 | |||
| 好好好,行,行,行,那上去吧,走吧。 | 0.083 | 0.056 | 0.883 | |||
| Chinese translation service?你需要帮助吗? | 0.444 | 0.293 | 0.938 | |||
| 董董事长最近常跟一个舞舞女接触。 | 0.467 | 0.134 | 0.691 | |||
| 在下深夜前来，想必大人知道所谓何事。 | 0.062 | 0.010 | 0.973 | |||
| 所以大家一定把七个声调念准确。 | 0.071 | 0.011 | 0.918 | |||
| It's not magic maomo. It's physics. Come with me. I'll show you. | 0.067 | 0.017 | 0.918 | |||
| 不是,我说实话,宣老师,哎,你这个科法,你后面的词,别慌。 | 0.182 | 0.118 | 0.844 | |||
| 流程图作业图，生产过程图解。 | 0.000 | 0.000 | 0.949 | |||
| 就更不能让佳阳为了逃避去选择文晓华。 | 0.118 | 0.019 | 0.938 | |||
| 今天中午食堂有什么好吃的吗？ | 0.000 | 0.000 | 0.898 | |||
| 由于后面足语比较长,所以句子构成了道庄。 | 0.111 | 0.043 | 0.941 | |||
| 送入两瓶好酒，我没收啊。 | 0.300 | 0.246 | 0.848 | |||
| 哎，言归正传啊，我今天来聊聊我的大学生活哦，我当时是在美国上的。 | 0.107 | 0.075 | 0.922 | |||
| 为了不让你再犯错呢，今天又是星期天，我放你一天，你让我清清静。 | 0.111 | 0.088 | 0.906 | |||
| 经过一些处理,经过一些加工,就是 | 0.000 | 0.000 | 0.961 | |||
| 这是白水禅院的法源送来的，想请大人通融放了他。 | 0.095 | 0.015 | 0.703 | |||
| 给少瑜送出的信发出几天了，已经四天了，可是什么消息都没有。 | 0.077 | 0.049 | 0.918 |