Update the docs for nemotron multi-lingual ASR model #728
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
|
|
@@ -265,6 +265,39 @@ for await (const chunk of audioClient.transcribeStreaming('/path/to/audio.wav')) | |||||
| } | ||||||
| ``` | ||||||
|
|
||||||
| #### Multilingual Language Codes | ||||||
|
|
||||||
| When using a multilingual ASR model (e.g. `nvidia-nemotron-3.5-asr-streaming-multilingual-0.6b`), set `language` to a BCP-47 language code to hint the expected language. | ||||||
|
|
||||||
| | Code | Language | Code | Language | | ||||||
| |------|----------|------|----------| | ||||||
| | `en-US` | English (US) | `en-GB` | English (UK) | | ||||||
| | `zh-CN` | Chinese (Simplified) | `ja-JP` | Japanese | | ||||||
| | `ko-KR` | Korean | `de-DE` | German | | ||||||
| | `fr-FR` | French | `fr-CA` | French (Canada) | | ||||||
| | `es-ES` | Spanish (Spain) | `es-US` | Spanish (US) | | ||||||
| | `it-IT` | Italian | `pt-BR` | Portuguese (Brazil) | | ||||||
| | `pt-PT` | Portuguese (Portugal) | `ru-RU` | Russian | | ||||||
| | `ar-AR` | Arabic | `hi-IN` | Hindi | | ||||||
| | `nl-NL` | Dutch | `pl-PL` | Polish | | ||||||
| | `sv-SE` | Swedish | `da-DK` | Danish | | ||||||
| | `fi-FI` | Finnish | `cs-CZ` | Czech | | ||||||
| | `ro-RO` | Romanian | `hu-HU` | Hungarian | | ||||||
| | `sk-SK` | Slovak | `bg-BG` | Bulgarian | | ||||||
| | `el-GR` | Greek | `et-EE` | Estonian | | ||||||
| | `hr-HR` | Croatian | `lt-LT` | Lithuanian | | ||||||
| | `lv-LV` | Latvian | `sl-SL` | Slovenian | | ||||||
| | `uk-UA` | Ukrainian | `he-IL` | Hebrew | | ||||||
| | `nb-NO` | Norwegian (Bokmål) | `nn-NO` | Norwegian (Nynorsk) | | ||||||
| | `th-TH` | Thai | `tr-TR` | Turkish | | ||||||
| | `vi-VN` | Vietnamese | `auto` | Auto-detect | | ||||||
|
|
||||||
| ```typescript | ||||||
| // Multilingual example | ||||||
| audioClient.settings.language = 'zh-CN'; // Chinese | ||||||
|
Contributor
There was a problem hiding this comment.
Suggested change
|
||||||
| audioClient.settings.language = 'auto'; // Auto-detect | ||||||
|
Contributor
There was a problem hiding this comment.
Suggested change
|
||||||
| ``` | ||||||
|
|
||||||
| ### Embedded Web Service | ||||||
|
|
||||||
| Start a local HTTP server that exposes an OpenAI-compatible API: | ||||||
|
|
||||||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -441,6 +441,39 @@ while let Some(chunk) = stream.next().await { | |
| } | ||
| ``` | ||
|
|
||
| #### Multilingual Language Codes | ||
|
|
||
| When using a multilingual ASR model (e.g. `nvidia-nemotron-3.5-asr-streaming-multilingual-0.6b`), set `language` to a BCP-47 language code to hint the expected language. | ||
|
|
||
| | Code | Language | Code | Language | | ||
| |------|----------|------|----------| | ||
| | `en-US` | English (US) | `en-GB` | English (UK) | | ||
| | `zh-CN` | Chinese (Simplified) | `ja-JP` | Japanese | | ||
| | `ko-KR` | Korean | `de-DE` | German | | ||
| | `fr-FR` | French | `fr-CA` | French (Canada) | | ||
| | `es-ES` | Spanish (Spain) | `es-US` | Spanish (US) | | ||
| | `it-IT` | Italian | `pt-BR` | Portuguese (Brazil) | | ||
| | `pt-PT` | Portuguese (Portugal) | `ru-RU` | Russian | | ||
| | `ar-AR` | Arabic | `hi-IN` | Hindi | | ||
|
rui-ren marked this conversation as resolved.
|
||
| | `nl-NL` | Dutch | `pl-PL` | Polish | | ||
| | `sv-SE` | Swedish | `da-DK` | Danish | | ||
| | `fi-FI` | Finnish | `cs-CZ` | Czech | | ||
| | `ro-RO` | Romanian | `hu-HU` | Hungarian | | ||
| | `sk-SK` | Slovak | `bg-BG` | Bulgarian | | ||
| | `el-GR` | Greek | `et-EE` | Estonian | | ||
| | `hr-HR` | Croatian | `lt-LT` | Lithuanian | | ||
| | `lv-LV` | Latvian | `sl-SL` | Slovenian | | ||
|
rui-ren marked this conversation as resolved.
|
||
| | `uk-UA` | Ukrainian | `he-IL` | Hebrew | | ||
| | `nb-NO` | Norwegian (Bokmål) | `nn-NO` | Norwegian (Nynorsk) | | ||
| | `th-TH` | Thai | `tr-TR` | Turkish | | ||
| | `vi-VN` | Vietnamese | `auto` | Auto-detect | | ||
|
|
||
| ```rust | ||
| // Multilingual example | ||
| let audio_client = model.create_audio_client() | ||
|
Contributor
There was a problem hiding this comment. Let's change this code section to the following. session.settings.language = Some("zh-CN".into()); // Chinese (Simplified)
session.settings.language = Some("auto".into()); // Auto-detect language |
||
| .language("zh-CN"); // Chinese | ||
| ``` | ||
|
|
||
| ### Embedded Web Service | ||
|
|
||
| Start a local HTTP server that exposes an OpenAI-compatible REST API: | ||
|
|
||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can we move these sections into the READMEs for the live audio transcription samples? These sections are currently listed in the SDK READMEs, which a customer will likely not see.