Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Riva streaming s2t client #99

Merged

Conversation

ydharavath
Copy link
Contributor

Previously, when processing a folder of audio files using riva nmt streaming s2t client, the output in output.txt is overwritten with each new file processed. This results in only the last audio file's output being retained in the file.

So now the client is updated so that the files are not overwritten but appended and the output will now be shown in json format in the output file

@rmittal-github rmittal-github changed the base branch from main to release/2.17.0 September 23, 2024 06:48
@rmittal-github rmittal-github merged commit df55be7 into nvidia-riva:release/2.17.0 Sep 23, 2024
1 check passed
rmittal-github added a commit that referenced this pull request Sep 30, 2024
* Add DNT (do not translate) support in S2S and S2T clients (#91)

* Add list_models option for s2s/s2t clients (#93)

* Support custom_configuration param for ASR clients (#92)

* Adding AST support for offline client

* Updating cli keywords

* exposing custom_configuration to cli

* Code formatting

* Throwing expection for invalid custom configurations

* Updating help message

* Updating client test

* Trim unwanted whitespaces while reading phrases file (#97)

* Add list_models option for ASR clients (#94)

* Update NMT text client to report tokens/sec (#90)

* performance metric-translation/sec updated

* performance metric-translations/sec updated

* Update riva_nmt_t2t_client.cc

* Update riva_nmt_t2t_client.cc

* updated perf metric and new line added

* updated perf metric and new line deleted

* Update riva_nmt_t2t_client.cc

* Update riva_nmt_t2t_client.cc

* Update riva_nmt_t2t_client.cc

* Update riva_nmt_t2t_client.cc

* Update riva_nmt_t2t_client.cc

* Update riva_nmt_t2t_client.cc

* Update riva_nmt_t2t_client.cc

* Update riva_nmt_t2t_client.cc

* Update riva_nmt_t2t_client.cc

---------

Co-authored-by: Yuvaraj Dharavath <[email protected]>

* Support to set max speakers for offline diarization (#98)

* fix: accept input for max_speaker_count in riva_asr_client

* update: default max_speaker_count to 3

* fix: rename input field to diarization_max_speakers

* fix: var name for consistency

* Fix output file dump for S2T client (#99)

* updated

* performance metric-translations/sec updated

* updated t2t client

* updated perf metric and new line added

* Update streaming_s2t_client.cc

* Update streaming_s2t_client.h

* riva streaming s2t client updated

* updated t2t client

* streaming s2t client updated

* Update streaming_s2t_client.h

* Update riva_nmt_streaming_s2t_client.cc

* Update riva_nmt_streaming_s2t_client.cc

* Update riva_nmt_t2t_client.cc

* Update streaming_s2t_client.cc

* Update streaming_s2t_client.h

* Update client_call.h

* Update streaming_s2t_client.cc

* updated streaming s2t client

* unwanted changes removed

* extra line removed

* extra line removed

* updated t2t client

* updated

* streaming_s2t_client updated

* s2t client audio procesed updated

* extra lines removed

---------

Co-authored-by: Manisha Johnson <[email protected]>
Co-authored-by: Yuvaraj Dharavath <[email protected]>

* update SHA of common repo

---------

Co-authored-by: shiralal <[email protected]>
Co-authored-by: sarane22 <[email protected]>
Co-authored-by: ydharavath <[email protected]>
Co-authored-by: Yuvaraj Dharavath <[email protected]>
Co-authored-by: Prabhsimran Singh <[email protected]>
Co-authored-by: Manisha Johnson <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants