3a:I[603186,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/32s25lphed-tr.js","/_next/static/chunks/0xg3tmq1q5uhz.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/2tbc_4m20jg4-.js"],"PageMetadata"] 3b:I[831915,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/32s25lphed-tr.js","/_next/static/chunks/0xg3tmq1q5uhz.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/2tbc_4m20jg4-.js"],"SearchResultsImage"] 3c:I[430295,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/32s25lphed-tr.js","/_next/static/chunks/0xg3tmq1q5uhz.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/2tbc_4m20jg4-.js"],""] 3d:I[299632,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/32s25lphed-tr.js","/_next/static/chunks/0xg3tmq1q5uhz.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/2tbc_4m20jg4-.js"],"default"] 3e:I[400402,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/32s25lphed-tr.js","/_next/static/chunks/0xg3tmq1q5uhz.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/2tbc_4m20jg4-.js"],"EndpointCTA"] 3f:I[331699,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/32s25lphed-tr.js","/_next/static/chunks/0xg3tmq1q5uhz.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/2tbc_4m20jg4-.js"],"ModelContent"] 45:I[776240,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/32s25lphed-tr.js","/_next/static/chunks/0xg3tmq1q5uhz.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/2tbc_4m20jg4-.js"],"default"] 46:I[946424,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/32s25lphed-tr.js","/_next/static/chunks/0xg3tmq1q5uhz.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/2tbc_4m20jg4-.js"],"default"] 37:["$","$L3a",null,{"hasPartnerEndpoint":false}] 40:Tb0a,## Model Overview Conformer-CTC (around 120M parameters) is trained on ASRSet with over 4100 hours of Spanish (es-US) speech. The model transcribes speech in lower case Spanish alphabet along with spaces and apostrophes. ## Model Architecture Conformer-CTC model is a non-autoregressive variant of Conformer model for Automatic Speech Recognition which uses CTC loss/decoding instead of Transducer. For more information, refer to the [Conformer-CTC Model](https://docs.nvidia.com/nemo-framework/user-guide/latest/nemotoolkit/asr/models.html#conformer-ctc) documentation. ## License/Terms of Use GOVERNING TERMS: The use of this model is governed by the NVIDIA Community Model License (found at https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/). # Disclaimer AI models generate responses and outputs based on complex algorithms and machine learning techniques, and those responses or outputs may be inaccurate or indecent. By testing this model, you assume the risk of any harm caused by any response or output of the model. Please do not upload any confidential information or personal data. Your use is logged for security. # References * [Paper](https://arxiv.org/abs/2005.08100) * [Conformer](https://docs.nvidia.com/nemo-framework/user-guide/latest/nemotoolkit/asr/models.html#conformer) ## Model Architecture **Architecture Type:** Convolutional Neural Network + Transformer
**Network Architecture:** Conformer Encoder with CTC Decoder
## Input **Input Type(s):** Audio in Spanish
**Input Format(s):** Linear PCM 16-bit 1 channel
## Output **Output Type(s):** Text String in Text String in Spanish
## Software Integration **Supported Operating System(s):**
* Linux
## Model Version * Conformer-CTC-L_spe256_es-US_3.1
# Inference **Engine:** Triton
**Test Hardware:**
* NVIDIA A10
* NVIDIA A100
* NVIDIA A30
* NVIDIA H100
* NVIDIA Jetson Orin
* NVIDIA L4
* NVIDIA L40
* NVIDIA Turing T4
* NVIDIA Volta V100
## Ethical Considerations (For NVIDIA Models Only): NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards. Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).41:T917,Field | Response :------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------- Intended Applications & Domains: | Speech Transcription Types: | Speech Transcription Intended Users: | Data Scientists in Contact Center Transcription, Video Conferencing Transcription, Virtual Assistants, etc Output: | Transcribed text with timestamps and confidence scores Describe how the model works: | Model transcribes audio input into text for the input language Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: | Age, Gender, National Origin Technical Limitations: | Transcripts may not be 100% accurate. Accuracy varies based on the characteristics of input audio (Domain, Use Case, Accent, Noise, Speech Type, Context of speech, etc.) Verified to have met prescribed NVIDIA quality standards: | Yes Performance Metrics: | Word Error Rate (WER), Silence Robustness (Characters/mins of silent audio), Latency (in milliseconds), Throughput (Total audio processed per unit of time) Potential Known Risks: | Not recommended for word-for-word transcription as accuracy varies based on the characteristics of input audio (domain, use case, accent, noise, speech type, and context of speech) Licensing: | https://developer.nvidia.com/riva/ga/license42:T81f,Field | Response :----------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------- Generatable or reverse engineerable personally-identifiable information (PII)? | None Was consent obtained for any PII used? | Yes Protected class data used to create this model? | Age, Gender, Linguistic Background, National Origin How often is dataset reviewed? | Before Release Is a mechanism in place to honor data subject right of access or deletion of personal data? | No If PII collected for the development of the model, was it collected directly by NVIDIA? | PII not collected by NVIDIA for development of model If PII collected for the development of the model by NVIDIA, do you maintain or have access to disclosures made to data subjects? | Not applicable If PII collected for the development of this AI model, was it minimized to only what was required? | Yes Is there provenance for all datasets used in training? | Yes Does data labeling (annotation, metadata) comply with privacy laws? | Yes Is data compliant with data subject requests for data correction or removal, if such a request was made? | The data is compliant where applicable, but is not applicable for all data.43:T688,### Getting Started Riva uses gRPC APIs. Instructions below demonstrate usage of <%- name %> model using Python gRPC client. ### Prerequisites You will need a system with Git and Python 3+ installed. ### Install Riva Python Client ```bash pip install nvidia-riva-client ``` ### Download Python Client Download Python client code by cloning Python Client Repository. ```bash git clone https://github.com/nvidia-riva/python-clients.git ``` ### Run Python Client Open a command terminal and execute below command to transcribe audio. Make sure you have a speech file in 16-bit Mono format in WAV/OGG/OPUS container. If you have generated the API key, it will be auto-populated in the command. ```bash python python-clients/scripts/asr/transcribe_file.py \ --server grpc.nvcf.nvidia.com:443 --use-ssl \ --metadata function-id "<%- nvcfFunctionId %>" \ --metadata "authorization" "Bearer <%- apiKey %>" \ --language-code es-US \ --input-file ``` ### Support for gRPC clients in other languages Riva uses gRPC APIs. Proto files can be downloaded from Riva gRPC Proto files and compiled to target language using Protoc compiler. Example Riva clients in C++ and Python languages are provided below. * Python Client Repository * C++ Client Repository 44:T6fb,## Step 1. Generate API Key ::generate-api-key ## Step 2. Pull and Run the NIM ```bash $ docker login nvcr.io Username: $oauthtoken Password: ``` Refer to [Supported Models](https://docs.nvidia.com/nim/riva/asr/latest/getting-started.html#supported-models) for full list of models. ```bash export NGC_API_KEY= docker run -it --rm --name=riva-asr \ --runtime=nvidia \ --gpus '"device=0"' \ --shm-size=8GB \ -e NGC_API_KEY \ -e NIM_HTTP_API_PORT=9000 \ -e NIM_GRPC_API_PORT=50051 \ -p 9000:9000 \ -p 50051:50051 \ -e NIM_TAGS_SELECTOR=name=conformer-ctc-riva-es-us,mode=str \ nvcr.io/nim/nvidia/riva-asr:1.3.0 ``` It may take a up to 30 minutes depending on your network speed, for the container to be ready and start accepting requests from the time the docker container is started. ## Step 3. Test the NIM Open a new terminal and run following command to check if the service is ready to handle inference requests ```bash curl -X 'GET' 'http://localhost:9000/v1/health/ready' ``` If the service is ready, you get a response similar to the following. ```bash {"ready":true} ``` Install the Riva Python client package ```bash sudo apt-get install python3-pip pip install nvidia-riva-client ``` Download Riva sample clients ```bash git clone https://github.com/nvidia-riva/python-clients.git ``` Run Speech to Text inference in streaming modes. Riva ASR supports Mono, 16-bit audio in WAV, OPUS and FLAC formats. ```bash python3 python-clients/scripts/asr/transcribe_file.py --server 0.0.0.0:50051 --input-file --language-code es-US ``` For more details on getting started with this NIM, visit the [Riva ASR NIM Docs](https://docs.nvidia.com/nim/riva/asr/latest/overview.html). 38:[["$","div",".3",{"className":"relative","children":[["$","div",null,{"className":"relative flex min-h-[194px] w-full flex-col overflow-hidden p-md sm:p-ml bg-manitoulinLightBlack","children":[["$","$L3b",null,{"alt":"","className":"object-cover object-center !left-1/2 z-10 !w-1/2 brightness-20 lg:brightness-75","fill":true,"priority":true,"src":"https://assets.ngc.nvidia.com/products/api-catalog/images/conformer-ctc-asr.jpg","style":{"maskImage":"linear-gradient(to left, rgba(0,0,0,1), rgba(0,0,0,0))"}}],["$","div",null,{"className":"z-30 mx-auto flex w-full max-w-screen-xl min-w-0 flex-1 flex-col items-start justify-between gap-md lg:flex-row lg:gap-ml","children":["$","section",null,{"aria-describedby":"resource-description","aria-labelledby":"resource-name","className":"flex w-full min-w-0 flex-col lg:flex-1","children":["$","div",null,{"className":"flex flex-col gap-1.5 whitespace-pre-wrap","children":[["$","$L3c",null,{"className":"w-fit text-ml text-n300 lowercase hover:text-n050","href":"/nvidia","children":"NVIDIA"}],["$","div",null,{"className":"flex flex-col items-start gap-3 lg:flex-row lg:items-center","children":[["$","h1",null,{"className":"max-w-full text-lg leading-heading font-medium break-words text-primary","data-testid":"resource-name","id":"resource-name","children":"conformer-ctc-asr"}],[["$","span","AVAILABLE",{"className":"nv-badge nv-badge--kind-solid h-[18px] py-0","data-testid":"nv-badge","ref":"$undefined","children":["$undefined","Downloadable"]}]],"$undefined"]}],["$","p",null,{"className":"max-w-[85ch] text-ms text-primary","id":"resource-description","children":"Automatic speech recognition model that transcribes speech in lower case Spanish with record-setting accuracy and performance"}],["$","div",null,{"className":"flex w-full flex-col items-start gap-md lg:flex-row lg:items-end lg:justify-between","children":[["$","div",null,{"className":"flex w-full min-w-0 flex-wrap gap-sm lg:flex-1","children":["$","$L3d",null,{"artifactType":"ENDPOINT","density":"standard","labels":["ASR","NVIDIA NIM","NVIDIA Riva","Spanish","nimType:endpoint:nim_type_run_anywhere","streaming","usecase:endpoint:usecase_speech_to_text"],"searchRoutePath":"/models"}]}],["$","div",null,{"className":"z-30 flex w-full flex-row justify-start gap-ms sm:justify-end lg:w-auto lg:shrink-0","children":["$undefined",["$","$L3e",null,{"cta":{"text":"Run Anywhere - Notify Me","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/","nim_available_override_url":"https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/riva-asr"},"isNIMAccessRestricted":"$undefined","isNIMAvailable":true}]]}]]}]]}]}]}],["$","div",null,{"className":"pointer-events-none absolute right-0 bottom-0 left-0 z-20 h-30 bg-gradient-to-t to-transparent from-manitoulinLightBlack via-manitoulinLightBlack/70"}]]}],["$","div",null,{"className":"px-4 mx-auto flex max-w-screen-xl flex-col pt-0 lg:px-0","data-body-background":"light-black","children":["$","section",null,{"className":"flex w-full flex-col justify-between rounded-4 border-manitoulinBorderColor bg-manitoulinDarkBlack sm:rounded-6 lg:rounded-8 p-ms lg:p-lg","children":["$","$L3f",null,{"artifact":{"artifactType":"ENDPOINT","name":"conformer-ctc-asr","displayName":"conformer-ctc-asr","publisher":"nvidia","shortDescription":"Automatic speech recognition model that transcribes speech in lower case Spanish with record-setting accuracy and performance","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/conformer-ctc-asr.jpg","labels":"$38:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:0:props:children:props:labels","attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"},{"key":"last_month_api_invocation_count","value":"35"},{"key":"last_month_download_count","value":"0"}],"updatedDate":"2025-04-10T15:19:39.201Z","bias":"Field | Response\n:---------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------\nParticipation considerations from adversely impacted groups ([protected classes](https://calcivilrights.ca.gov/disputeresolution/protected-characteristics/)) in model design and testing: | Age, Gender, Linguistic Background\nMeasures taken to mitigate against unwanted bias: | Used custom dataset to validate model performance across gender, age, and linguistic demographics","canGuestDownload":true,"createdDate":"2024-11-18T17:43:39.026Z","description":"$40","explainability":"$41","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$42","safetyAndSecurity":"Field | Response\n:---------------------------------------------------|:----------------------------------\nModel Application(s): | Speech Transcription\nDescribe the life-critical impacts (if present). | Not Applicable for Licensed Use Cases per [NVIDIA RIVA License Agreement](https://developer.nvidia.com/riva/ga/license)\nUse Case Restriction(s): | Abide by https://developer.nvidia.com/riva/ga/license\nModel and Dataset Restriction(s): | Dataset access restrictions\nDescribe access restrictions (if any): | The Principle of Least Privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training and dataset license constraints adhered to."},"endpointName":"conformer-ctc-asr","endpointSpec":{"namespace":"qc69jvmznzxy","updatedDate":"2026-08-10T20:29:38.390Z","nvcfFunctionId":"50124cf2-fb60-4a8c-9d25-d85b85199526","createdDate":"2024-11-18T17:43:39.407Z","attributes":{"apiDocsUrl":"https://docs.nvidia.com/nim/riva/asr/latest/protos.html","termsOfUse":"GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use; and the use of this model is governed by the NVIDIA AI Foundation Models Community License.\n","showUnavailableBanner":false,"cta":"$38:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:1:props:children:1:props:cta","usage":"$43","deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$44"}]},"artifactName":"conformer-ctc-asr"},"isLoginRequired":true,"playgroundElement":"$45","publisherName":"nvidia","searchParams":{"model":"conformer-ctc-asr"},"tabs":[{"label":"Experience","bare":true,"icon":"play","kind":"default","id":"experience","href":"/nvidia/conformer-ctc-asr","aliases":["/nvidia/conformer-ctc-asr/experience"]},{"label":"Model Card","icon":"book","kind":"default","id":"modelcard","href":"/nvidia/conformer-ctc-asr/modelcard","aliases":"$undefined"},{"label":"Try API","kind":"default","id":"api","href":"/nvidia/conformer-ctc-asr/api","aliases":"$undefined"},{"label":"Deploy","kind":"default","id":"deploy","href":"/nvidia/conformer-ctc-asr/deploy","aliases":"$undefined"}]}]}]}]]}]] 39:["$","$L46",null,{"spec":"$38:0:props:children:1:props:children:props:children:props:endpointSpec"}]