Add pipeline tag and library name
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
@@ -1,12 +1,14 @@
|
|
1 |
---
|
2 |
-
|
|
|
3 |
datasets:
|
4 |
- VocalNet/VoiceAssitant-430K-vocalnet
|
5 |
- VocalNet/UltraChat-vocalnet
|
6 |
language:
|
7 |
- en
|
8 |
-
|
9 |
-
|
|
|
10 |
---
|
11 |
|
12 |
## 🎧 VocalNet-1B Model Card
|
@@ -277,263 +279,73 @@ VocalNet-1B was evaluated on [OpenAudioBench](https://huggingface.co/datasets/ba
|
|
277 |
<td style="padding: 10px; border: 1px solid #ddd;"><u>6.22</u></td>
|
278 |
</tr>
|
279 |
<tr>
|
280 |
-
<td
|
281 |
-
<td
|
282 |
-
<td
|
283 |
-
<td
|
284 |
-
<td
|
285 |
-
<td
|
286 |
-
<td
|
287 |
-
</tr>
|
288 |
-
<tr>
|
289 |
-
<td style="padding: 10px; border: 1px solid #ddd;">s→s</td>
|
290 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>6.48</b></td>
|
291 |
-
<td style="padding: 10px; border: 1px solid #ddd;">64.1</td>
|
292 |
-
<td style="padding: 10px; border: 1px solid #ddd;">3.75</td>
|
293 |
-
<td style="padding: 10px; border: 1px solid #ddd;">3.99</td>
|
294 |
-
</tr>
|
295 |
-
<tr>
|
296 |
-
<td rowspan="2" style="padding: 10px; border: 1px solid #ddd;">Qwen2.5-Omni</td>
|
297 |
-
<td rowspan="2" style="padding: 10px; border: 1px solid #ddd;">8B</td>
|
298 |
-
<td style="padding: 10px; border: 1px solid #ddd;">s→t</td>
|
299 |
-
<td style="padding: 10px; border: 1px solid #ddd;">6.01</td>
|
300 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><u>79.0</u></td>
|
301 |
-
<td style="padding: 10px; border: 1px solid #ddd;">5.89</td>
|
302 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><u>6.88</u></td>
|
303 |
-
</tr>
|
304 |
-
<tr>
|
305 |
-
<td style="padding: 10px; border: 1px solid #ddd;">s→s</td>
|
306 |
-
<td style="padding: 10px; border: 1px solid #ddd;">5.73</td>
|
307 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>76.3</b></td>
|
308 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><u>5.59</u></td>
|
309 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>6.70</b></td>
|
310 |
-
</tr>
|
311 |
-
<tr>
|
312 |
-
<td rowspan="2" style="padding: 10px; border: 1px solid #ddd;">VocalNet-8B (VA)</td>
|
313 |
-
<td rowspan="2" style="padding: 10px; border: 1px solid #ddd;">8B</td>
|
314 |
-
<td style="padding: 10px; border: 1px solid #ddd;">s→t</td>
|
315 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><u>7.05</u></td>
|
316 |
-
<td style="padding: 10px; border: 1px solid #ddd;">77.1</td>
|
317 |
-
<td style="padding: 10px; border: 1px solid #ddd;">6.15</td>
|
318 |
-
<td style="padding: 10px; border: 1px solid #ddd;">6.34</td>
|
319 |
-
</tr>
|
320 |
-
<tr>
|
321 |
-
<td style="padding: 10px; border: 1px solid #ddd;">s→s</td>
|
322 |
-
<td style="padding: 10px; border: 1px solid #ddd;">6.30</td>
|
323 |
-
<td style="padding: 10px; border: 1px solid #ddd;">71.4</td>
|
324 |
-
<td style="padding: 10px; border: 1px solid #ddd;">5.24</td>
|
325 |
-
<td style="padding: 10px; border: 1px solid #ddd;">5.81</td>
|
326 |
-
</tr>
|
327 |
-
<tr>
|
328 |
-
<td rowspan="2" style="padding: 10px; border: 1px solid #ddd;">VocalNet-8B</td>
|
329 |
-
<td rowspan="2" style="padding: 10px; border: 1px solid #ddd;">8B</td>
|
330 |
-
<td style="padding: 10px; border: 1px solid #ddd;">s→t</td>
|
331 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>7.12</b></td>
|
332 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>79.5</b></td>
|
333 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><u>6.24</u></td>
|
334 |
-
<td style="padding: 10px; border: 1px solid #ddd;">6.48</td>
|
335 |
-
</tr>
|
336 |
-
<tr>
|
337 |
-
<td style="padding: 10px; border: 1px solid #ddd;">s→s</td>
|
338 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><u>6.37</u></td>
|
339 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><u>73.1</u></td>
|
340 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>5.67</b></td>
|
341 |
-
<td style="padding: 10px; border: 1px solid #ddd;">6.16</td>
|
342 |
-
</tr>
|
343 |
-
</tbody>
|
344 |
-
</table>
|
345 |
-
</div>
|
346 |
-
|
347 |
-
#### Response Alignment and Acoustic Quality
|
348 |
-
<div align="center">
|
349 |
-
<table style="margin: 0 auto; text-align: center; border-collapse: collapse; font-size: 14px;">
|
350 |
-
<tbody>
|
351 |
-
<tr style="background-color: #f2f2f2;">
|
352 |
-
<td rowspan="2" style="padding: 10px; border: 1px solid #ddd;">Model</td>
|
353 |
-
<td colspan="2" style="padding: 10px; border: 1px solid #ddd;">AlpacaEval</td>
|
354 |
-
<td colspan="2" style="padding: 10px; border: 1px solid #ddd;">LLaMA Questions</td>
|
355 |
-
<td colspan="2" style="padding: 10px; border: 1px solid #ddd;">TriviaQA</td>
|
356 |
-
<td colspan="2" style="padding: 10px; border: 1px solid #ddd;">Web Questions</td>
|
357 |
-
<td colspan="2" style="padding: 10px; border: 1px solid #ddd;">Avg</td>
|
358 |
-
</tr>
|
359 |
-
<tr>
|
360 |
-
<td style="padding: 10px; border: 1px solid #ddd;">WER</td>
|
361 |
-
<td style="padding: 10px; border: 1px solid #ddd;">UTMOS</td>
|
362 |
-
<td style="padding: 10px; border: 1px solid #ddd;">WER</td>
|
363 |
-
<td style="padding: 10px; border: 1px solid #ddd;">UTMOS</td>
|
364 |
-
<td style="padding: 10px; border: 1px solid #ddd;">WER</td>
|
365 |
-
<td style="padding: 10px; border: 1px solid #ddd;">UTMOS</td>
|
366 |
-
<td style="padding: 10px; border: 1px solid #ddd;">WER</td>
|
367 |
-
<td style="padding: 10px; border: 1px solid #ddd;">UTMOS</td>
|
368 |
-
<td style="padding: 10px; border: 1px solid #ddd;">WER</td>
|
369 |
-
<td style="padding: 10px; border: 1px solid #ddd;">UTMOS</td>
|
370 |
-
</tr>
|
371 |
-
<tr>
|
372 |
-
<td colspan="11" style="padding: 10px; border: 1px solid #ddd; font-weight: bold; background-color: #e6f3ff;">Tiny Models</td>
|
373 |
-
</tr>
|
374 |
-
<tr>
|
375 |
-
<td style="padding: 10px; border: 1px solid #ddd;">Mini-Omni</td>
|
376 |
-
<td style="padding: 10px; border: 1px solid #ddd;">20.78</td>
|
377 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.429</td>
|
378 |
-
<td style="padding: 10px; border: 1px solid #ddd;">5.20</td>
|
379 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.428</td>
|
380 |
-
<td style="padding: 10px; border: 1px solid #ddd;">7.43</td>
|
381 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.428</td>
|
382 |
-
<td style="padding: 10px; border: 1px solid #ddd;">8.51</td>
|
383 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.433</td>
|
384 |
-
<td style="padding: 10px; border: 1px solid #ddd;">8.66</td>
|
385 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.430</td>
|
386 |
-
</tr>
|
387 |
-
<tr>
|
388 |
-
<td style="padding: 10px; border: 1px solid #ddd;">SLAM-Omni</td>
|
389 |
-
<td style="padding: 10px; border: 1px solid #ddd;">5.52</td>
|
390 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.439</td>
|
391 |
-
<td style="padding: 10px; border: 1px solid #ddd;">5.55</td>
|
392 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.467</td>
|
393 |
-
<td style="padding: 10px; border: 1px solid #ddd;">6.16</td>
|
394 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.470</td>
|
395 |
-
<td style="padding: 10px; border: 1px solid #ddd;">6.50</td>
|
396 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.461</td>
|
397 |
-
<td style="padding: 10px; border: 1px solid #ddd;">6.17</td>
|
398 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.464</td>
|
399 |
</tr>
|
400 |
<tr>
|
401 |
-
<td
|
402 |
-
<td
|
403 |
-
<td
|
404 |
-
<td
|
405 |
-
<td
|
406 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>5.97</b></td>
|
407 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>4.499</b></td>
|
408 |
-
<td style="padding: 10px; border: 1px solid #ddd;">6.40</td>
|
409 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.489</td>
|
410 |
-
<td style="padding: 10px; border: 1px solid #ddd;">5.66</td>
|
411 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>4.495</b></td>
|
412 |
</tr>
|
413 |
<tr>
|
414 |
-
<td style="padding: 10px; border: 1px solid #ddd;">
|
415 |
-
<td
|
416 |
-
<td
|
417 |
-
<td
|
418 |
-
<td
|
419 |
-
<td
|
420 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.486</td>
|
421 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>4.88</b></td>
|
422 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>4.493</b></td>
|
423 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>5.31</b></td>
|
424 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.491</td>
|
425 |
-
</tr>
|
426 |
-
<tr>
|
427 |
-
<td colspan="11" style="padding: 10px; border: 1px solid #ddd; font-weight: bold; background-color: #e6f3ff;">Base Models</td>
|
428 |
-
</tr>
|
429 |
-
<tr>
|
430 |
-
<td style="padding: 10px; border: 1px solid #ddd;">LLaMA-Omni</td>
|
431 |
-
<td style="padding: 10px; border: 1px solid #ddd;">6.00</td>
|
432 |
-
<td style="padding: 10px; border: 1px solid #ddd;">3.942</td>
|
433 |
-
<td style="padding: 10px; border: 1px solid #ddd;">10.00</td>
|
434 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.003</td>
|
435 |
-
<td style="padding: 10px; border: 1px solid #ddd;">20.93</td>
|
436 |
-
<td style="padding: 10px; border: 1px solid #ddd;">3.965</td>
|
437 |
-
<td style="padding: 10px; border: 1px solid #ddd;">14.60</td>
|
438 |
-
<td style="padding: 10px; border: 1px solid #ddd;">3.935</td>
|
439 |
-
<td style="padding: 10px; border: 1px solid #ddd;">15.90</td>
|
440 |
-
<td style="padding: 10px; border: 1px solid #ddd;">3.956</td>
|
441 |
-
</tr>
|
442 |
-
<tr>
|
443 |
-
<td style="padding: 10px; border: 1px solid #ddd;">Freeze-Omni</td>
|
444 |
-
<td style="padding: 10px; border: 1px solid #ddd;">14.33</td>
|
445 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.377</td>
|
446 |
-
<td style="padding: 10px; border: 1px solid #ddd;">14.20</td>
|
447 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.417</td>
|
448 |
-
<td style="padding: 10px; border: 1px solid #ddd;">20.39</td>
|
449 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.404</td>
|
450 |
-
<td style="padding: 10px; border: 1px solid #ddd;">18.25</td>
|
451 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.398</td>
|
452 |
-
<td style="padding: 10px; border: 1px solid #ddd;">18.31</td>
|
453 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.401</td>
|
454 |
-
</tr>
|
455 |
-
<tr>
|
456 |
-
<td style="padding: 10px; border: 1px solid #ddd;">GLM-4-Voice</td>
|
457 |
-
<td style="padding: 10px; border: 1px solid #ddd;">18.71</td>
|
458 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.025</td>
|
459 |
-
<td style="padding: 10px; border: 1px solid #ddd;">14.45</td>
|
460 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.152</td>
|
461 |
-
<td style="padding: 10px; border: 1px solid #ddd;">8.33</td>
|
462 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.306</td>
|
463 |
-
<td style="padding: 10px; border: 1px solid #ddd;">6.08</td>
|
464 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.214</td>
|
465 |
-
<td style="padding: 10px; border: 1px solid #ddd;">8.99</td>
|
466 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.228</td>
|
467 |
-
</tr>
|
468 |
-
<tr>
|
469 |
-
<td style="padding: 10px; border: 1px solid #ddd;">Baichuan-Omni-1.5</td>
|
470 |
-
<td style="padding: 10px; border: 1px solid #ddd;">20.84</td>
|
471 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.082</td>
|
472 |
-
<td style="padding: 10px; border: 1px solid #ddd;">22.82</td>
|
473 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.332</td>
|
474 |
-
<td style="padding: 10px; border: 1px solid #ddd;">22.36</td>
|
475 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.401</td>
|
476 |
-
<td style="padding: 10px; border: 1px solid #ddd;">23.29</td>
|
477 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.350</td>
|
478 |
-
<td style="padding: 10px; border: 1px solid #ddd;">22.67</td>
|
479 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.347</td>
|
480 |
-
</tr>
|
481 |
-
<tr>
|
482 |
-
<td style="padding: 10px; border: 1px solid #ddd;">MiniCPM-o</td>
|
483 |
-
<td style="padding: 10px; border: 1px solid #ddd;">15.35</td>
|
484 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.102</td>
|
485 |
-
<td style="padding: 10px; border: 1px solid #ddd;">5.73</td>
|
486 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.228</td>
|
487 |
-
<td style="padding: 10px; border: 1px solid #ddd;">8.08</td>
|
488 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.128</td>
|
489 |
-
<td style="padding: 10px; border: 1px solid #ddd;">8.94</td>
|
490 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.125</td>
|
491 |
-
<td style="padding: 10px; border: 1px solid #ddd;">8.72</td>
|
492 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.137</td>
|
493 |
</tr>
|
494 |
<tr>
|
495 |
-
<td
|
496 |
-
<td
|
497 |
-
<td
|
498 |
-
<td
|
499 |
-
<td
|
500 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>1.13</b></td>
|
501 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.339</td>
|
502 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.68</td>
|
503 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.363</td>
|
504 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>2.63</b></td>
|
505 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.342</td>
|
506 |
</tr>
|
507 |
<tr>
|
508 |
<td style="padding: 10px; border: 1px solid #ddd;">VocalNet-8B (VA)</td>
|
509 |
-
<td
|
510 |
-
<td
|
511 |
-
<td
|
512 |
-
<td
|
513 |
-
<td
|
514 |
-
<td
|
515 |
-
<td
|
516 |
-
<td
|
517 |
-
<td
|
518 |
-
<td
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
519 |
</tr>
|
|
|
520 |
<tr>
|
521 |
-
|
522 |
-
<td style="padding: 10px; border: 1px solid #ddd;">4.71</td>
|
523 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><u>4.489</u></td>
|
524 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><u>2.68</u></td>
|
525 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><u>4.500</u></td>
|
526 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><u>4.04</u></td>
|
527 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><u>4.482</u></td>
|
528 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><b>3.11</b></td>
|
529 |
-
<td style="padding as: 10px; border: 1px solid #ddd;"><b>4.492</b></td>
|
530 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><u>3.56</u></td>
|
531 |
-
<td style="padding: 10px; border: 1px solid #ddd;"><u>4.489</u></td>
|
532 |
</tr>
|
|
|
533 |
</tbody>
|
534 |
</table>
|
535 |
</div>
|
536 |
|
|
|
|
|
537 |
### ✍️ Citation
|
538 |
If you find our work useful, please cite:
|
539 |
```bib
|
|
|
1 |
---
|
2 |
+
base_model:
|
3 |
+
- meta-llama/Llama-3.2-1B-Instruct
|
4 |
datasets:
|
5 |
- VocalNet/VoiceAssitant-430K-vocalnet
|
6 |
- VocalNet/UltraChat-vocalnet
|
7 |
language:
|
8 |
- en
|
9 |
+
license: apache-2.0
|
10 |
+
pipeline_tag: audio-text-to-text
|
11 |
+
library_name: transformers
|
12 |
---
|
13 |
|
14 |
## 🎧 VocalNet-1B Model Card
|
|
|
279 |
<td style="padding: 10px; border: 1px solid #ddd;"><u>6.22</u></td>
|
280 |
</tr>
|
281 |
<tr>
|
282 |
+
<td style="padding: 10px; border: 1px solid #ddd;">Minmo*</td>
|
283 |
+
<td style="padding: 10px; border: 1px solid #ddd;">8B</td>
|
284 |
+
<td>s→t</td>
|
285 |
+
<td>-</td>
|
286 |
+
<td>78.9</td>
|
287 |
+
<td>4.83</td>
|
288 |
+
<td>5.50</td>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
289 |
</tr>
|
290 |
<tr>
|
291 |
+
<td>s→s</td>
|
292 |
+
<td><b>6.48<br></td>
|
293 |
+
<td>64.1</td>
|
294 |
+
<td>3.75</td>
|
295 |
+
<td>3.99</td>
|
|
|
|
|
|
|
|
|
|
|
|
|
296 |
</tr>
|
297 |
<tr>
|
298 |
+
<td style="padding: 10px; border: 1px solid #ddd;">Qwen2.5-Omni</td>
|
299 |
+
<td>s→t</td>
|
300 |
+
<td>6.01</td>
|
301 |
+
<td><u>79.0</u></td>
|
302 |
+
<td>5.89</td>
|
303 |
+
<td><u>6.88</u></td>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
304 |
</tr>
|
305 |
<tr>
|
306 |
+
<td>s→s</td>
|
307 |
+
<td>5.73</td>
|
308 |
+
<td><b>76.3<br></td>
|
309 |
+
<td><u>5.59</u></td>
|
310 |
+
<td><b>6.70<br></td>
|
|
|
|
|
|
|
|
|
|
|
|
|
311 |
</tr>
|
312 |
<tr>
|
313 |
<td style="padding: 10px; border: 1px solid #ddd;">VocalNet-8B (VA)</td>
|
314 |
+
<td><u>7.05</u></td>
|
315 |
+
<td><b>4.490<br></td>
|
316 |
+
<td>77.1</td>
|
317 |
+
<td>4.503</td>
|
318 |
+
<td>6.15</td>
|
319 |
+
<td><b>4.499<br></td>
|
320 |
+
<td><u>4.21</u></td>
|
321 |
+
<td><u>4.485</u></td>
|
322 |
+
<td>4.26</td>
|
323 |
+
<td><b>4.493<br></td>
|
324 |
+
</tr>
|
325 |
+
<tr>
|
326 |
+
<td>VocalNet-8B</td>
|
327 |
+
<td><b>7.12<br></td>
|
328 |
+
<td><u>4.489</u></td>
|
329 |
+
<td><b>79.5<br></td>
|
330 |
+
<td>4.500</td>
|
331 |
+
<td><u>6.24</u></td>
|
332 |
+
<td>4.482</td>
|
333 |
+
<td>3.11</td>
|
334 |
+
<td>4.492</td>
|
335 |
+
<td><u>3.56</u></td>
|
336 |
+
<td><u>4.489</u></td>
|
337 |
</tr>
|
338 |
+
<thead>
|
339 |
<tr>
|
340 |
+
<th class="tg-c3ow" colspan="11"></th>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
341 |
</tr>
|
342 |
+
</thead>
|
343 |
</tbody>
|
344 |
</table>
|
345 |
</div>
|
346 |
|
347 |
+
</details>
|
348 |
+
|
349 |
### ✍️ Citation
|
350 |
If you find our work useful, please cite:
|
351 |
```bib
|