Skip to content

Commit

Permalink
Update index.html.md
Browse files Browse the repository at this point in the history 
Adding new diarization parameters
  • Loading branch information
@jnorsa-amberscript
jnorsa-amberscript authored Aug 27, 2024
1 parent 8edd9e1 commit 25b048f
Showing 1 changed file with 14 additions and 2 deletions.
16 changes: 14 additions & 2 deletions source/index.html.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -239,7 +239,7 @@ Upload a file for transcription.
| language | `en` | `af-za`, `sq-al`, `am-et`, `ar`, `hy-am`, `az-az`, `id-id`, `eu-es`, `bn-bd`, `bn-in`, `bs-ba`, `bg`, `my-mm`, `ca`, `cmn`, `hr`, `cs`, `da`, `nl`, `en-au`, `en-uk`, `en`, `et-ee`, `fa-ir`, `fil-ph`, `fi`, `nl-be`, `fr-ca`, `fr`, `gl-es`, `ka-ge`, `de-at`, `de-ch`, `de`, `el`, `gu-in`, `iw-il`, `hi`, `hu`, `is-is`, `it`, `ja`, `jv-id`, `kn-in`, `km-kh`, `ko`, `lo-la`, `lv`, `lt`, `mk-mk`, `ms`, `ml-in`, `mr-in`, `mn-mn`, `ne-np`, `no`, `pl`, `pt-br`, `pt`, `pa-guru-in`, `ro`, `ru`, `sr-rs`, `si-lk`, `sk`, `sl`, `es`, `su-id`, `sw-ke`, `sw-tz`, `sv`, `ta-in`, `ta-my`, `ta-sg`, `ta-lk`, `te-in`, `th-th`, `tr`, `uk-ua`, `ur-in`, `ur-pk`, `uz-uz`, `vi-vn`, `zu-za`, `auto` |
| transcriptionType | `transcription` | `transcription`, `captions`, `translatedSubtitles` |
| jobType | `direct` | `perfect`, `direct` |
| numberOfSpeakers | `2` | `1`, `2`, `3`, `4`, `5` |
| numberOfSpeakers | `2` | `-1`, `0`, `1`, `2`, `3`, `4`, `5` |
| callbackUrl (OPTIONAL) | NONE | `YOUR_CALLBACK_URL` |
| glossaryId (OPTIONAL) | NONE | `YOUR_GLOSSARY_ID` |
| transcriptionStyle (OPTIONAL - Transcript only) | `cleanread` | `cleanread`, `verbatim` |
Expand Down Expand Up @@ -316,6 +316,12 @@ or
- [List your previously created glossaries](#get-a-list-of-glossaries) and pick an `id` of the glossary that you want to
use as `glossaryId` in your upload request.

### Number of speaker

If you know the number of speakers present in your audio file, you can define ite by using a number between 1 and 5. It is the most accurate approach to recognize each speaker;
If you do not know the number of speakers, please use the value '0';
If your file contains several channels and each speaker is assigned to a specific channel, you can use the value '-1'.

### Automatic language identification

You can let the automatic speech recognition engine determine the language of uploaded media automatically. To do so,
Expand Down Expand Up @@ -434,7 +440,7 @@ curl --request POST --url 'https://api.amberscript.com/api/jobs/upload-media-fro
| language | `en` | `af-za`, `sq-al`, `am-et`, `ar`, `hy-am`, `az-az`, `id-id`, `eu-es`, `bn-bd`, `bn-in`, `bs-ba`, `bg`, `my-mm`, `ca`, `cmn`, `hr`, `cs`, `da`, `nl`, `en-au`, `en-uk`, `en`, `et-ee`, `fa-ir`, `fil-ph`, `fi`, `nl-be`, `fr-ca`, `fr`, `gl-es`, `ka-ge`, `de-at`, `de-ch`, `de`, `el`, `gu-in`, `iw-il`, `hi`, `hu`, `is-is`, `it`, `ja`, `jv-id`, `kn-in`, `km-kh`, `ko`, `lo-la`, `lv`, `lt`, `mk-mk`, `ms`, `ml-in`, `mr-in`, `mn-mn`, `ne-np`, `no`, `pl`, `pt-br`, `pt`, `pa-guru-in`, `ro`, `ru`, `sr-rs`, `si-lk`, `sk`, `sl`, `es`, `su-id`, `sw-ke`, `sw-tz`, `sv`, `ta-in`, `ta-my`, `ta-sg`, `ta-lk`, `te-in`, `th-th`, `tr`, `uk-ua`, `ur-in`, `ur-pk`, `uz-uz`, `vi-vn`, `zu-za`, `auto` |
| transcriptionType | `transcription` | `transcription`, `captions`, `translatedSubtitles` |
| jobType | `direct` | `perfect`, `direct` |
| numberOfSpeakers | `2` | `1`, `2`, `3`, `4`, `5` |
| numberOfSpeakers | `2` | `-1`, `0`, `1`, `2`, `3`, `4`, `5` |
| sourceUrl | `` | "https://www.learningcontainer.com/wp-content/uploads/2020/05/sample-mp4-file.mp4" |
| callbackUrl (OPTIONAL) | NONE | `YOUR_CALLBACK_URL` |
| glossaryId (OPTIONAL) | NONE | `YOUR_GLOSSARY_ID` |
Expand Down Expand Up @@ -501,6 +507,12 @@ Otherwise, you will get a callback informing you that your job was successfully
- `status` can either be `OPEN`, `DONE` or `ERROR`.
### Number of speaker
If you know the number of speakers present in your audio file, you can define ite by using a number between 1 and 5. It is the most accurate approach to recognize each speaker;
If you do not know the number of speakers, please use the value '0';
If your file contains several channels and each speaker is assigned to a specific channel, you can use the value '-1'.
### Automatic language identification
You can let the automatic speech recognition engine determine the language of uploaded media automatically. To do so,
Expand Down

0 comments on commit 25b048f

Please sign in to comment.