Commits · rjzevallos/streaming

Delete simulstreaming_whisper.py

1e63610
verified

rjzevallos commited on Nov 21

Delete token_buffer.py

99cfc7b
verified

rjzevallos commited on Nov 21

Update app.py (user changes)

a2e856a

rjzevallos commited on Nov 19

chore(rebuild): trigger Space rebuild (empty commit)

91d2b7f

rjzevallos commited on Nov 19

Feat(server): support WHISPER_MODEL_NAME/WHISPER_MODEL_SIZE (e.g. tiny); prefer local <name>.pt; improve error guidance

88e4729

rjzevallos commited on Nov 19

Fix(app): init ASR model in background; add error handling; remove share=True

bcc3253

rjzevallos commited on Nov 19

Fix: send 'FINISH' text over WebSocket on stop to match server

921076a

rjzevallos commited on Nov 19

Fix: send 'FINISH' text over WebSocket on stop to match server

408e16b

rjzevallos commited on Nov 19

Fix: send 'FINISH' text over WebSocket on stop to match server

89b1173

rjzevallos commited on Nov 19

Fix: send 'FINISH' text over WebSocket on stop to match server

20547d7

rjzevallos commited on Nov 19

WS: support binary finish marker; client sends 0xFF.. marker (client only sends binary chunks)

4ae7ed6

rjzevallos commited on Nov 19

WS: accept both binary audio chunks and text control messages (FINISH/RESET)

b809819

rjzevallos commited on Nov 19

Fix: send 'FINISH' text over WebSocket on stop to match server

d711f84

rjzevallos commited on Nov 19

UI: Add visible Start/Stop recording buttons with improved layout

071c394

rjzevallos commited on Nov 19

Implement true streaming: WebSocket for real-time chunk processing

1e30c31

rjzevallos commited on Nov 18

Refactor: Use native Gradio audio component for reliable microphone capture

0eb9991

rjzevallos commited on Nov 18

Fix: Optimize build to prevent OOM - download model at runtime instead of build time

3e8e10c

rjzevallos commited on Nov 18

Improve UI: Fix audio recording with better button detection and feedback

f8ce589

rjzevallos commited on Nov 18

Fix: Use openai-whisper library for model loading instead of torch.hub

3b07c9e

rjzevallos commited on Nov 18

Add simulstreaming_whisper module, update requirements, improve Dockerfile and model handling

d860e14

rjzevallos commited on Nov 18

Merge remote changes and remove space.yaml

7b7fdec

rjzevallos commited on Nov 18

Fixed

f4275b5

rjzevallos commited on Nov 18

Update space.yaml

54ea9e1
verified

rjzevallos commited on Nov 18

Whisper Gradio

87071e6

rjzevallos commited on Nov 18

initial commit

ac1c7b9
verified

rjzevallos commited on Nov 17

Spaces:

rjzevallos
/

streaming

Runtime error

Commit History

Delete simulstreaming_whisper.py

1e63610
verified

Delete token_buffer.py

99cfc7b
verified

Update app.py (user changes)

a2e856a

chore(rebuild): trigger Space rebuild (empty commit)

91d2b7f

Feat(server): support WHISPER_MODEL_NAME/WHISPER_MODEL_SIZE (e.g. tiny); prefer local <name>.pt; improve error guidance

88e4729

Fix(app): init ASR model in background; add error handling; remove share=True

bcc3253

Fix: send 'FINISH' text over WebSocket on stop to match server

921076a

Fix: send 'FINISH' text over WebSocket on stop to match server

408e16b

Fix: send 'FINISH' text over WebSocket on stop to match server

89b1173

Fix: send 'FINISH' text over WebSocket on stop to match server

20547d7

WS: support binary finish marker; client sends 0xFF.. marker (client only sends binary chunks)

4ae7ed6

WS: accept both binary audio chunks and text control messages (FINISH/RESET)

b809819

Fix: send 'FINISH' text over WebSocket on stop to match server

d711f84

UI: Add visible Start/Stop recording buttons with improved layout

071c394

Implement true streaming: WebSocket for real-time chunk processing

1e30c31

Refactor: Use native Gradio audio component for reliable microphone capture

0eb9991

Fix: Optimize build to prevent OOM - download model at runtime instead of build time

3e8e10c

Improve UI: Fix audio recording with better button detection and feedback

f8ce589

Fix: Use openai-whisper library for model loading instead of torch.hub

3b07c9e

Add simulstreaming_whisper module, update requirements, improve Dockerfile and model handling

d860e14

Merge remote changes and remove space.yaml

7b7fdec

Fixed

f4275b5

Update space.yaml

54ea9e1
verified

Whisper Gradio

87071e6

initial commit

ac1c7b9
verified

Commit History

Delete simulstreaming_whisper.py 1e63610 verified

Delete token_buffer.py 99cfc7b verified

Update app.py (user changes) a2e856a

chore(rebuild): trigger Space rebuild (empty commit) 91d2b7f

Feat(server): support WHISPER_MODEL_NAME/WHISPER_MODEL_SIZE (e.g. tiny); prefer local <name>.pt; improve error guidance 88e4729

Fix(app): init ASR model in background; add error handling; remove share=True bcc3253

Fix: send 'FINISH' text over WebSocket on stop to match server 921076a

Fix: send 'FINISH' text over WebSocket on stop to match server 408e16b

Fix: send 'FINISH' text over WebSocket on stop to match server 89b1173

Fix: send 'FINISH' text over WebSocket on stop to match server 20547d7

WS: support binary finish marker; client sends 0xFF.. marker (client only sends binary chunks) 4ae7ed6

WS: accept both binary audio chunks and text control messages (FINISH/RESET) b809819

Fix: send 'FINISH' text over WebSocket on stop to match server d711f84

UI: Add visible Start/Stop recording buttons with improved layout 071c394

Implement true streaming: WebSocket for real-time chunk processing 1e30c31

Refactor: Use native Gradio audio component for reliable microphone capture 0eb9991

Fix: Optimize build to prevent OOM - download model at runtime instead of build time 3e8e10c

Improve UI: Fix audio recording with better button detection and feedback f8ce589

Fix: Use openai-whisper library for model loading instead of torch.hub 3b07c9e

Add simulstreaming_whisper module, update requirements, improve Dockerfile and model handling d860e14

Merge remote changes and remove space.yaml 7b7fdec

Fixed f4275b5

Update space.yaml 54ea9e1 verified

Whisper Gradio 87071e6

initial commit ac1c7b9 verified

Delete simulstreaming_whisper.py

1e63610
verified

Delete token_buffer.py

99cfc7b
verified

Update app.py (user changes)

a2e856a

chore(rebuild): trigger Space rebuild (empty commit)

91d2b7f

Feat(server): support WHISPER_MODEL_NAME/WHISPER_MODEL_SIZE (e.g. tiny); prefer local <name>.pt; improve error guidance

88e4729

Fix(app): init ASR model in background; add error handling; remove share=True

bcc3253

Fix: send 'FINISH' text over WebSocket on stop to match server

921076a

Fix: send 'FINISH' text over WebSocket on stop to match server

408e16b

Fix: send 'FINISH' text over WebSocket on stop to match server

89b1173

Fix: send 'FINISH' text over WebSocket on stop to match server

20547d7

WS: support binary finish marker; client sends 0xFF.. marker (client only sends binary chunks)

4ae7ed6

WS: accept both binary audio chunks and text control messages (FINISH/RESET)

b809819

Fix: send 'FINISH' text over WebSocket on stop to match server

d711f84

UI: Add visible Start/Stop recording buttons with improved layout

071c394

Implement true streaming: WebSocket for real-time chunk processing

1e30c31

Refactor: Use native Gradio audio component for reliable microphone capture

0eb9991

Fix: Optimize build to prevent OOM - download model at runtime instead of build time

3e8e10c

Improve UI: Fix audio recording with better button detection and feedback

f8ce589

Fix: Use openai-whisper library for model loading instead of torch.hub

3b07c9e

Add simulstreaming_whisper module, update requirements, improve Dockerfile and model handling

d860e14

Merge remote changes and remove space.yaml

7b7fdec

Fixed

f4275b5

Update space.yaml

54ea9e1
verified

Whisper Gradio

87071e6

initial commit

ac1c7b9
verified