NVIDIA Conformer-Transducer Large (es)

| | |

This model transcribes speech in lowercase Spanish alphabet including spaces, and was trained on a composite dataset comprising of 1340 hours of Spanish speech. It is a "large" variant of Conformer-Transducer, with around 120 million parameters.See the model architecture section and NeMo documentation for complete architecture details.

NVIDIA NeMo: Training

To train, fine-tune or play with the model you will need to install NVIDIA NeMo . We recommend you install it after you've installed latest Pytorch version.

pip install nemo_toolkit['all']

How to Use this Model

The model is available for use in the NeMo toolkit [3], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.

Automatically instantiate the model

import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained("nvidia/stt_es_conformer_transducer_large")

Transcribing using Python

First, let's get a sample

wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav

Then simply do:

asr_model.transcribe(['2086-149220-0033.wav'])

Transcribing many audio files

python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py 
 pretrained_name="nvidia/stt_es_conformer_transducer_large" 
 audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"

Input

This model accepts 16000 Hz Mono-channel Audio (wav files) as input.

Output

This model provides transcribed speech as a string for a given audio sample.

Model Architecture

Conformer-Transducer model is an autoregressive variant of Conformer model [1] for Automatic Speech Recognition which uses Transducer loss/decoding instead of CTC Loss. You may find more info on the detail of this model here: Conformer-Transducer Model .

Training

The NeMo toolkit [3] was used for training the models for over several hundred epochs. These model are trained with this example script and this base config .

The tokenizers for these models were built using the text transcripts of the train set with this script .

Datasets

All the models in this collection are trained on a composite dataset (NeMo ASRSET) comprising of 1340 hours of Spanish speech:

• Mozilla Common Voice 7.0 (Spanish) - 289 hours after data cleaning
• Multilingual LibriSpeech (Spanish) - 801 hours after data cleaning
• Voxpopuli transcribed subset (Spanish) - 110 hours after data cleaning
• Fisher dataset (Spanish) - 140 hours after data cleaning

Performance

The list of the available models in this collection is shown in the following table. Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding.

Version	Tokenizer	Vocabulary Size	MCV 7.0 Dev	MCV 7.0 Test	MLS Dev	MLS Test	Voxpopuli Dev	Voxpopuli Test	Fisher Dev	Fisher Test	Train Dataset
1.8.0	SentencePiece Unigram	1024	4.6	5.2	2.7	3.2	4.7	6.0	14.7	14.8	NeMo ASRSET 2.0

Limitations

Since this model was trained on publicly available speech datasets, the performance of this model might degrade for speech which includes technical terms, or vernacular that the model has not been trained on. The model might also perform worse for accented speech.

NVIDIA Riva: Deployment

NVIDIA Riva , is an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, on edge, and embedded. Additionally, Riva provides:

• World-class out-of-the-box accuracy for the most common languages with model checkpoints trained on proprietary data with hundreds of thousands of GPU-compute hours
• Best in class accuracy with run-time word boosting (e.g., brand and product names) and customization of acoustic model, language model, and inverse text normalization
• Streaming speech recognition, Kubernetes compatible scaling, and enterprise-grade support

Although this model isn't supported yet by Riva, the list of supported models is here . Check out Riva live demo .

References

• [1] Conformer: Convolution-augmented Transformer for Speech Recognition
• [2] Google Sentencepiece Tokenizer
• [3] NVIDIA NeMo Toolkit

Licence

License to use this model is covered by the CC-BY-4.0 . By downloading the public and release version of the model, you accept the terms and conditions of the CC-BY-4.0 license.

.hf-sanitized.hf-sanitized-p0Qh-PiXOiPA1ve85HaEH img {display: inline;} 以上模型将转录包括空格在内的小写西班牙字母的语音，并在包含1340小时西班牙语语音的复合数据集上进行训练。它是Conformer-Transducer的"large"变体，具有约1.2亿个参数。完整的架构细节见模型架构部分和 NeMo documentation 。NVIDIA NeMo: 训练。要训练、微调或使用模型，您需要安装 NVIDIA NeMo 。我们建议在安装最新版本的Pytorch之后再安装它。如何使用此模型。该模型可在NeMo工具包[3]中使用，并可用作预训练的检查点进行推断或在另一个数据集上进行微调。自动实例化模型。使用Python进行转录。首先，让我们获得一个示例。然后只需执行。转录多个音频文件。输入。该模型接受16000 Hz单声道音频（wav文件）作为输入。输出。该模型为给定音频样本提供转录的语音字符串。模型架构。Conformer-Transducer模型是Conformer模型[1]的自回归变体，用于自动语音识别，它使用转换器损失/解码而不是CTC损失。有关此模型的详细信息，请参阅此处: Conformer-Transducer Model 。训练。使用NeMo工具包[3]对模型进行了数百个时期的训练。这些模型使用了这个 example script 和这个 base config 进行了训练。这些模型的分词器是使用训练集的文本转录建立的，使用了这个 script 。数据集。此集合中的所有模型都是在包含1340小时西班牙语语音的复合数据集(NeMo ASRSET)上进行训练的。性能。此集合中可用模型的列表显示在下表中。使用贪婪解码报告ASR模型的性能，以词错误率（WER%）为指标。局限性。由于此模型是在公开可用的语音数据集上进行训练的，所以该模型在包含技术术语或模型未经训练的口头语言的语音中的性能可能会下降。该模型在口音语音中的表现可能也会更差。NVIDIA Riva:部署。 NVIDIA Riva 是一种可以在本地、所有云端、多云、混合、边缘和嵌入式上部署的加速语音AI SDK。此外，Riva还提供以下功能: 世界级的开箱即用准确性，具有在专有数据上训练的模型检查点，使用数十万个GPU计算小时。具有实时词语提升（例如品牌和产品名称）以及对声学模型、语言模型和逆文本归一化的定制的最佳准确性。流式语音识别、与Kubernetes兼容的扩展能力和企业级支持。尽管此模型尚未受到Riva的支持，但 list of supported models is here 。有关详细信息，请查看 Riva live demo 。参考资料。[1] Conformer: Convolution-augmented Transformer for Speech Recognition [2] Google Sentencepiece Tokenizer [3] NVIDIA NeMo Toolkit 。许可证。使用此模型的许可证受到 CC-BY-4.0 的约束。通过下载模型的公开和发布版本，您同意接受 CC-BY-4.0 许可条款和条件。.hf-sanitized.hf-sanitized-p0Qh-PiXOiPA1ve85HaEH img {display: inline;}