The End of Awkward AI Transcriptions

Talk transcript

1. 0:00

   Hi, everyone. I'm Travis.

2. 0:03

   Hello, I'm Byungjoong.

3. 0:04

   I'm Jaehan.

4. 0:06

   And we're here to talk to you today about the end of awkward AI transcripts from NVIDIA.

5. 0:12

   So what we're gonna go over today is basically how we develop models at NVIDIA Speech, um, for NVIDIA Speech AI. We're gonna go over the model architectures, um, our main approach to how we develop models for our customer base, um, the entire development process, and our focus on deployment and customization.

6. 0:32

   So who are we? Well, we're with NVIDIA Riva. We focus on enterprise-level s- um, speech AI model deployment. We cover speech translation, text-to-speech development, speech recognition, speech translation. Basically everything so that, um, we can at an enterprise level allow customers to provide the best possible conversational AI that is possible.

7. 0:56

   And we... Our focus is generally on low latency, highly efficient models that, uh, can be used, um, on embedded devices.

8. 1:06

   So, um, at NVIDIA there's generally, like, four categories we focus on when we're thinking about model development. First is robustness. Are our models going to work in noisy environments a- as well as they work in clean environments?

9. 1:20

   What type of sound quality are we trying to meet? Are we going to worry about telephony? Are we going to worry about a bunch of environmental contamination factors? Um, we also consider ourselves with coverage.

10. 1:32

    What are the domains that our customer base wants? Is it gonna be medical? Is it going to be entertainment? Is it going to be, um, just straight up call center based?

11. 1:42

    What is the language demands that we need? Do we wanna focus on monolingual development or multilingual development? How will dialect play into our model cases? And is there a pro- problem of code switching that we should accommodate for in development?

12. 1:57

    We also focus on personalization. We want to make sure that our customers are able to have the exact model that they need for their needs. Sometimes we gotta focus on target speaker AI.

13. 2:09

    Sometimes we gotta focus on word boosting for uncommon vocabulary. Sometimes we just get down and dirty with old-fashioned text normalization FST models just to make sure that you're getting the exact output you want.

14. 2:21

    And then finally, we focus on deployment cases. How does speed and accuracy trade off here? Which is more important, or do we want a middle ground of the two?

15. 2:30

    Um, do we want our models to be, have h- high variety, or are we gonna focus on efficiency and kinda lead like, um, the Swiss ar- army knives in, in our back pocket?

16. 2:42

    So what type of models do we use to accomplish this? Well, if you're from a speech AI background, a lot of this is really familiar stuff. First off, we still rely on the old-fashioned CTC models, 'cause we keep finding that non-autoregression, um, decoding cases is really optimal if you need high speed inference, especially in streaming environments where

17. 3:04

    you can just run CTC over a, um, chunk data set, use that as a streaming model, and you can move on with your, um, next project.

18. 3:14

    But of course, we still like high accuracy. So when we find that just simply non-aggression is not, um, a ideal, then we s- rely on the old-fashioned RNN-T or, um, you use TDT models, which is a variant, um, developed at NVIDIA.

19. 3:29

    Here we've used the audio output of an encoder with an internal LM so that we can have aut- autoregressive streaming setups, um, for deployment. Then sometimes you want even more accuracy.

20. 3:43

    Sometimes you don't want to worry about streaming, in which case we also offer, um, attention encoder-decoder setups. We are all familiar with them at this point. Whisper, ChatGPT, LLMs, and yeah, we offer those here.

21. 3:59

    We find that they're really good if you want a highly accurate model, um, with less focus on alignment, and more importantly, accommodate a lot of ta- tasks within a single model.

22. 4:10

    We find, um, auto, um, we find transformer decoders really great when you need to incorporate speech translation, timestamp prediction, language identification, and speech recognition all within a single model with simple prompt changes.

23. 4:26

    But across all of our different, um, decoding platforms, we have one unifying tool, which is that our fundamental architecture is the Fast Conformer. Through a lot of empirical trials, we found that the original conformer model can be even greatly, um, subsampled so that instead of just the conventional forty millisecond time s- step compression, you can switch...

24. 4:48

    You can add in a next, another step of subsampling and get eighty millisecond compression. And we find that along with allowing you to have very small audio inputs and thus really lightens your memory load on training, it also makes training a lot more efficient because you can get way quicker conversions with, um, n- not as much data

25. 5:10

    as needed. Further, it allows really fast inference because now you're chunking all your data into just eighty millisecond time steps. And so we found that this is a really strong architecture that we have at the backbone of all of our previous m- um, decoding offerings.

26. 5:27

    And this allows us to split our model offerings into two options. On the left we have Riva Parakeet, which is focused on our streaming speech recognition cases, and this is where we put our CTC and our TDT models, and the focus is on streaming.

27. 5:44

    If you want speech recognition, speech translation, target speaker ASR, you're gonna run it through a K- Parakeet model so that you can have very fast, um, and efficient, um, recognition Meanwhile, on our other option, we have Riva Canary, which is where we put our fast conformer models.

28. 6:05

    This is where we focus on accuracy and mul- and multitask modeling. This is where we're going to get the best accuracy as possible while not really caring that much about speed, though we do push for strong speed.

29. 6:23

    And so be- being able to cover all this, we get a really, really comprehensive toolkit in which we can offer to our customers, um, a mixture of fast multitasking or high-accuracy models.

30. 6:36

    And most important is that our focus on we have the model to meet the need, as opposed to an idea that one model fits all. We focus on variety and coverage rather than, um, unifying and, um, keeping everything under one hood.

31. 6:57

    Given the success of the Parakeet ASR model, it can be easily extended to the multi-speaker and target-speaker, uh, scenario with the integration of the diarization model Sortformer. The Sortformer is a end-to-end neuron diarizer that following the rival time sorting principle.

32. 7:16

    In the simply words, it's standing for who comes first. So the Sortformer behaves as a bridge between the speaker timestamp from the diarization and the speaker token that can be recognized by the ASR model.

33. 7:29

    In our mo- in our model architecture development principle, we fuse the ASR encoder embedding and the Sortformer embedding through the speaker kernel in providing the full-fledged who spoke what and when problem.

34. 7:43

    And this objective, the, this model can be fine-tuned with a really simple objective similar to the any ASR model training, uh, perspective. And also, by feeding the model, or feeding the model with the option no query audio or not, we can make the model to conduct the target-speaker ASR task or the sing- or single multi-speaker, uh, ASR

35. 8:06

    task. And moreover, our unified model architecture consists of ASR encoder and Sortformer, but it can not only be applied in the parallel joint manner, but can also be used as the cascade system, just like conventional multi-speaker system.

36. 8:26

    Yeah, uh, we have additional models we offer to improve further accuracy, customization, and readability. Um, the voice activity detection, VAD, uh, detects speech segments for better noise robustness, and we offer DistilBERTaVAD and the MarbleNet-based VAD models.

37. 8:47

    The external language model, uh, rescores ASR transcription for better accuracy and customization. We have n-gram-based language models, uh, in our, uh, the Riva ASR pipelines. Text normalization and the inverse text normalization convert spoken terms to, uh, written forms in text for better readability, and we have, uh, the

38. 9:11

    WFST-based ITN models. Punctuation capitalization, PNC, uh, adds punctuation and capitalization to the transcription for better readability, and, uh, BERT-based PNC models is supported.

39. 9:27

    Uh, finally, the speaker diarization identifies, uh, multiple speakers in conversation, uh, and we have the Sortformer-based speaker diarization models, uh, in Cascade model, as well as the, uh, upcoming for the, uh, end-to-end, uh, models.

40. 9:50

    And so, um, given this level of customization, it doesn't, like, really surprise that, like, it pays off, um, when it comes to, um, rankings. On the Hugging Face Open ASR leaderboard, the majority of the top five models do come from NVIDIA, and all of it does is come down to this approach on a focus on customization and

41. 10:11

    variety. But, you know, rankings aren't everything. So let's try out a demo.

42. 10:19

    So let's say you're trying to run a recognition system, but you have a... but it, it's a song you're going over. Can our models work?

43. 10:27

    Living for the now, long as time allows. I'ma keep on switching different styles, keep creative on a cloud. Sweat is on my brow 'cause I'm running on these tracks just to keep the running back, you know the drill, the quarter back.

44. 10:37

    And I've been practicing my craft, dedicate this play to Kobe. What could be a bigger legacy than making it as-

45. 10:44

    Yeah, seems to work pretty well. Accurate transcription even in a noisy setting.

46. 10:53

    Okay, so that's our architectures, that's our approach to development. So how does it actually go into training? Is there anything special we do with training to, um, uh, to meet this demand?

47. 11:04

    And the answer is honestly not really. We really focus on to met the fundamentals when it comes to data development. Like many labs, um, our focus is on robustness when it comes to sourcing data, multilingual coverage, and a, a, an ear for dialect sensitivity.

48. 11:22

    We try and get as much language documentation as possible before, um, so that we know exactly what type of data spans we wanna get. We incorporate both open source and proprietary data, with the former allowing us to focus on variety and domain shift, while the latter lets us focus on high-quality NC data.

49. 11:44

    We incorporate pseudo-labeling, where we use, um, the top-of-the-line models that are available for commercial use, and we take transcripts from them, allowing us to benefit from further developments in the community and further developments from our own releases.

50. 12:01

    And then for training, again, a lot of it is just standard available stuff. Um, the NeMo research, um, toolkit that is used for our model training is an open source available, um, library available for anyone in the community to use.

51. 12:19

    It's, um, it's tools for GPU maximalization, data bucketing, um, high-speed data loading through the Lodse backend, all available for just general use. And so we just focus on this approach where we can maximize our data, we can maximize the, um, speed in which we can ingest data across different settings.

52. 12:41

    Most of our data is in stored on a object store infrastructure in which we can quickly migrate between different cluster settings.

53. 12:50

    And then for validation, just as much as with training, we focus on a nice mixture of coverage in both open source and proprietary data. We make sure that by the time data be-- by the time our models actually reach end users, we've gone through as much, um, bias and domain testing as possible across all possible language categories,

54. 13:14

    just to make sure that our models are as robust as possible.

55. 13:22

    The trained model, uh, is now deployed to, uh, NVIDIA Riva through NVIDIA NIM for low latency and high throughput inference. The high performance, uh, inference is powered by NVIDIA TensorRT optimizations, um, and the NVIDIA Triton Inference Server.

56. 13:41

    And it is available for gRPC-based microservice for low latency streaming, as well as the high throughput offline use cases. The NVIDIA Riva is fully containerized, and it can, uh, easily scale to hundreds of the, um, the parallel streams, and, uh, it can be run on-prem in any cloud at the edge or, uh, embedded platforms to

57. 14:05

    support a variety of the applications, including contact centers, consumer applications, and video conferencing.

58. 14:15

    NVIDIA NIM offers prebuilt container industry-standard API support for custom models, uh, and optimized inference engines.

59. 14:27

    So one of the pain point in real scenarios from customers is, um, customization, because every use case, um, uh, every application requires domain knowledge, including the medical terms in medical use case, um, menu names in food ordering, and, um, some of the acoustic conditions, telephony, uh, and noisy environment in contact

60. 14:52

    centers. So NVIDIA, uh, Riva offers, um, the, uh, customization features at every stages. So, uh, we can fine-tune our acoustic model from the Parakeet-based model, Canary-based models, and then we can fine-tune the n-gram, um, external language model, punctuation model, and the inverse text normalization models.

61. 15:17

    And also we offer the word boosting to, uh, recognize, uh, better on some of the, uh, product names, jargon, and context-specific, uh, knowledges.

62. 15:32

    So, um, we are offering our, uh, the Riva models in NVIDIA NIM. So, um, you can, um, visit, uh, our website, build.nvidia.com/explore/speech.

63. 15:47

    Then you can find more, um, the available, uh, Riva models, uh, in the website.

64. 15:56

    Here is the more thing, uh, how to get started with NVIDIA Riva, uh, quick starter guide, uh, developers pro-- uh, developers forum, and, uh, uh, the fine-tuning guide, how to fine-tune our models in the, in, uh, NeMo frameworks.

65. 16:19

    Yeah, so that's it. Thank you.

66. 16:22

    Thank you, everyone.

67. 16:22

    Thank you