Download samples/cases.json from VoiceHub/dacvae-tts-en-experiments: direct link, hf CLI and curl.
- Browser
- Download file 12.1 kB
-
https://huggingface.co/VoiceHub/dacvae-tts-en-experiments/resolve/main/samples/cases.json
- Command line
-
hf download hf://VoiceHub/dacvae-tts-en-experiments/samples/cases.json
-
curl -L -o cases.json https://huggingface.co/VoiceHub/dacvae-tts-en-experiments/resolve/main/samples/cases.json
12.1 kB
| [ | |
| { | |
| "uid": "echo-spk_1611", | |
| "speaker": "spk_1611", | |
| "voice": "male", | |
| "f0_hz": 110, | |
| "text": "Are they twins or just normal siblings?", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_1611.wav", | |
| "reference_text": "Well, the traffic was\u2014 actually, it wasn't traffic. It was a herd of sheep. On the highway. I don't know either. I just sat there, not making eye contact with any of them.", | |
| "reference_seconds": 10.36, | |
| "reference_dnsmos_ovrl": 3.633, | |
| "reference_utmos": 4.494, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_0620", | |
| "speaker": "spk_0620", | |
| "voice": "male", | |
| "f0_hz": 103, | |
| "text": "He must be disguised to avoid encounters with thieves.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_0620.wav", | |
| "reference_text": "Last night\u2014 actually, it was early this morning, around three\u2014 I found myself making up apologies for things nobody even remembers. It's a real waste of time, but the brain doesn't care.", | |
| "reference_seconds": 9.66, | |
| "reference_dnsmos_ovrl": 3.548, | |
| "reference_utmos": 4.485, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_0800", | |
| "speaker": "spk_0800", | |
| "voice": "female", | |
| "f0_hz": 187, | |
| "text": "The town of Norwich is located east of the center of the county.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_0800.wav", | |
| "reference_text": "The neighbor upstairs\u2014 wait, no, the one next door\u2014 keeps playing bagpipes. At midnight. I think they're practicing for a revolution or something.", | |
| "reference_seconds": 8.41, | |
| "reference_dnsmos_ovrl": 3.526, | |
| "reference_utmos": 4.446, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_0997", | |
| "speaker": "spk_0997", | |
| "voice": "male", | |
| "f0_hz": 142, | |
| "text": "Constrictor knots can also be quite effective as improvised hose clamps or cable ties.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_0997.wav", | |
| "reference_text": "I swear, if I have to see that one guy who\u2014 wait, not that bus, yesterday I mean, on the 42, some guy was playing music out loud and my daughter kept asking what it was and I just...", | |
| "reference_seconds": 9.98, | |
| "reference_dnsmos_ovrl": 3.611, | |
| "reference_utmos": 4.458, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_3299", | |
| "speaker": "spk_3299", | |
| "voice": "male", | |
| "f0_hz": 128, | |
| "text": "These two agencies co-operate in aspects of law enforcement, including their joint marine unit.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_3299.wav", | |
| "reference_text": "Remember when I used to complain about the subway? Well, today it was worse. This guy\u2014 he was eating a sandwich, right next to me, and the smell\u2014 I almost lost it.", | |
| "reference_seconds": 8.59, | |
| "reference_dnsmos_ovrl": 3.548, | |
| "reference_utmos": 4.407, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_3107", | |
| "speaker": "spk_3107", | |
| "voice": "female", | |
| "f0_hz": 173, | |
| "text": "It then became part of Poland.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_3107.wav", | |
| "reference_text": "God, I still think about that time at the coffee shop\u2014I waved at someone I thought I knew, but it was a stranger, and they just stared. Then I pretended to check my phone and walked away so fast\u2026", | |
| "reference_seconds": 10.73, | |
| "reference_dnsmos_ovrl": 3.626, | |
| "reference_utmos": 4.52, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_0878", | |
| "speaker": "spk_0878", | |
| "voice": "male", | |
| "f0_hz": 102, | |
| "text": "Will you be happy when I am in the earth?", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_0878.wav", | |
| "reference_text": "You know, I was walking home yesterday and I suddenly remembered that song we used to... well, not remember, I mean, it just popped into my head out of nowhere. The weirdest part is I hadn't thought about it in years.", | |
| "reference_seconds": 10.08, | |
| "reference_dnsmos_ovrl": 3.598, | |
| "reference_utmos": 4.354, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_2616", | |
| "speaker": "spk_2616", | |
| "voice": "male", | |
| "f0_hz": 121, | |
| "text": "She was involved in several record productions.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_2616.wav", | |
| "reference_text": "Okay, so\u2014 wait, no. The whole thing got moved to Thursday? I literally had Wednesday cleared and now I have to\u2014 I can't even... This is so messed up.", | |
| "reference_seconds": 9.61, | |
| "reference_dnsmos_ovrl": 3.597, | |
| "reference_utmos": 4.435, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_3855", | |
| "speaker": "spk_3855", | |
| "voice": "female", | |
| "f0_hz": 186, | |
| "text": "The Larson Brothers Airport is located in the town.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_3855.wav", | |
| "reference_text": "Well\u2014no wait\u2014my sunburn is literally glowing, I caught myself in the mirror and wow. It's like I'm a human tomato, but at least it's a cute tomato.", | |
| "reference_seconds": 9.15, | |
| "reference_dnsmos_ovrl": 3.61, | |
| "reference_utmos": 4.476, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_3812", | |
| "speaker": "spk_3812", | |
| "voice": "male", | |
| "f0_hz": 116, | |
| "text": "Flood gates were erected and drainage systems improved.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_3812.wav", | |
| "reference_text": "Honestly, I have no idea where I put that file. I thought I put it in my bag, but it's not here. And I looked everywhere\u2014 well, not everywhere, but in the usual places. It's probably in that stack of papers I've been avoiding.", | |
| "reference_seconds": 11.15, | |
| "reference_dnsmos_ovrl": 3.596, | |
| "reference_utmos": 4.369, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_2193", | |
| "speaker": "spk_2193", | |
| "voice": "male", | |
| "f0_hz": 119, | |
| "text": "He did not live to complete the development of his system.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_2193.wav", | |
| "reference_text": "It's funny\u2014well, not funny, but my hamster escaped his cage and I spent an hour looking for him. I was so scared he'd get into something, but he was just behind the couch, sleeping.", | |
| "reference_seconds": 10.87, | |
| "reference_dnsmos_ovrl": 3.591, | |
| "reference_utmos": 4.484, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_0929", | |
| "speaker": "spk_0929", | |
| "voice": "female", | |
| "f0_hz": 190, | |
| "text": "The land is volcanic in origin with mountains in the interior.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_0929.wav", | |
| "reference_text": "I mean, I was so burnt out I actually\u2014 hold on, I think I set my coffee down somewhere weird. Anyway, I spent an hour yesterday staring at the ceiling, and it was honestly the most productive I've been all month.", | |
| "reference_seconds": 9.89, | |
| "reference_dnsmos_ovrl": 3.544, | |
| "reference_utmos": 4.428, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_0516", | |
| "speaker": "spk_0516", | |
| "voice": "male", | |
| "f0_hz": 141, | |
| "text": "The Tuesday market is held by the blue bridge over the River Iro.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_0516.wav", | |
| "reference_text": "Well, I think you're overthinking it a little. Wait, no\u2014 I do that too. Sorry, I just mean\u2026 it's okay, it happens to everyone.", | |
| "reference_seconds": 6.97, | |
| "reference_dnsmos_ovrl": 3.532, | |
| "reference_utmos": 4.364, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_0441", | |
| "speaker": "spk_0441", | |
| "voice": "male", | |
| "f0_hz": 96, | |
| "text": "The evidence against Strafford was weak, and the impeachment failed.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_0441.wav", | |
| "reference_text": "The vet said\u2014 actually, she said it might be allergies? But now my dog's scratching so much he's losing fur, so I don't know if I misunderstood or if it's getting worse.", | |
| "reference_seconds": 9.47, | |
| "reference_dnsmos_ovrl": 3.557, | |
| "reference_utmos": 4.497, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_1664", | |
| "speaker": "spk_1664", | |
| "voice": "female", | |
| "f0_hz": 188, | |
| "text": "It is operated by the New York City Department of Parks and Recreation.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_1664.wav", | |
| "reference_text": "Ugh, I always take the wrong train. Wait, no\u2014 this is the express? I think? The map said something different but I'm not sure anymore.", | |
| "reference_seconds": 8.17, | |
| "reference_dnsmos_ovrl": 3.569, | |
| "reference_utmos": 4.492, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_1399", | |
| "speaker": "spk_1399", | |
| "voice": "male", | |
| "f0_hz": 128, | |
| "text": "Also that year, he collaborated with Evan Dando on a new Lemonheads album.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_1399.wav", | |
| "reference_text": "I don't really have plans this weekend, if I'm being honest. Which is fine, I guess. I mean, who needs a social life when you have Netflix and a cat, right? Actually, my cat is more social than me\u2014she has more friends.", | |
| "reference_seconds": 10.63, | |
| "reference_dnsmos_ovrl": 3.573, | |
| "reference_utmos": 4.335, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_2881", | |
| "speaker": "spk_2881", | |
| "voice": "male", | |
| "f0_hz": 129, | |
| "text": "Finally, lumping groups of one's own pieces together is usually poor strategy.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_2881.wav", | |
| "reference_text": "I honestly didn't think we'd have the same weekend off. I was planning to just clean the garage, but then my neighbor\u2014 oh, not you, my other neighbor\u2014 said they have extra tickets to the game.", | |
| "reference_seconds": 9.61, | |
| "reference_dnsmos_ovrl": 3.533, | |
| "reference_utmos": 4.443, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_2111", | |
| "speaker": "spk_2111", | |
| "voice": "female", | |
| "f0_hz": 228, | |
| "text": "Over time the couple has four more children, although William never warms to them.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_2111.wav", | |
| "reference_text": "Yes! Yes, yes, yes! This changes \u2014 okay, this changes everything, I can't believe I didn't\u2014 actually, I kind of can, but anyway, feeling overwhelmed in the best way.", | |
| "reference_seconds": 9.2, | |
| "reference_dnsmos_ovrl": 3.593, | |
| "reference_utmos": 4.307, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_1559", | |
| "speaker": "spk_1559", | |
| "voice": "male", | |
| "f0_hz": 139, | |
| "text": "The battle was of medium term significance, consolidating Royalist control of Yorkshire.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_1559.wav", | |
| "reference_text": "Maybe I should\u2019ve said something different that night, or\u2014wait, no, that was Monday, not Tuesday. Anyway it doesn\u2019t matter now, but my brain keeps circling back to it like a weird song stuck on repeat, and I\u2019m just tired of the melody.", | |
| "reference_seconds": 10.87, | |
| "reference_dnsmos_ovrl": 3.536, | |
| "reference_utmos": 4.453, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| }, | |
| { | |
| "uid": "echo-spk_3011", | |
| "speaker": "spk_3011", | |
| "voice": "male", | |
| "f0_hz": 99, | |
| "text": "Before guns were invented, armies had to throw bullets at each other and if a bullet touched you, you had to sit out until the next war.", | |
| "reference_audio": "/workspace/data/en/echo-refs/listen/spk_3011.wav", | |
| "reference_text": "It's funny\u2014I found that old photo of us at the fair, the one where your hat is all lopsided, and I just started laughing for no reason. Well, not no reason, you looked ridiculous.", | |
| "reference_seconds": 9.85, | |
| "reference_dnsmos_ovrl": 3.564, | |
| "reference_utmos": 4.448, | |
| "source": "SynDataLab-EN-Refs/echo-ref-speakers-4k-en" | |
| } | |
| ] |