You're looking at a specific version of this model. Jump to the model overview.
usamaehsan /llm-ears:b8a77841
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| mode |
None
|
experiment
|
None
|
| configs |
string
|
[{"layer": 32, "ctx": [0]}, {"layer": 32, "ctx": [0, 4, 12]}, {"layer": 24, "ctx": [0, 4, 12]}]
|
experiment: JSON list of {layer (1-32), ctx (list of context radii in frames), rff (random ReLU features, 0=off)}
|
| grid |
string
|
{"alpha": [0.0001, 0.001, 0.01, 0.1, 1.0], "smooth": [1, 5, 9], "tau": [0.2, 0.35, 0.5, 0.65], "min_run": [1, 3, 5]}
|
experiment: JSON search grid tuned on a 5% holdout
|
| n_fit |
integer
|
0
|
experiment: max dev-clean utterances (0 = all 2703)
|
| n_test |
integer
|
400
Min: 10 Max: 2620 |
experiment: test-clean utterances for WER
|
| n_llm |
integer
|
200
Max: 2620 |
experiment: test utterances also read by the LLM
|
| alignments |
string
|
experiment: alignments.json.gz from an earlier run
|
|
| seed |
integer
|
0
|
None
|
| audio |
string
|
listen: audio file
|
|
| bridge |
string
|
listen: bridge.safetensors from an experiment run
|
|
| question |
string
|
Write exactly what was said.
|
listen: what to ask the LLM
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'properties': {'alignments': {'format': 'uri',
'nullable': True,
'title': 'Alignments',
'type': 'string'},
'bridge': {'format': 'uri',
'nullable': True,
'title': 'Bridge',
'type': 'string'},
'report': {'format': 'uri',
'nullable': True,
'title': 'Report',
'type': 'string'},
'text': {'nullable': True, 'title': 'Text', 'type': 'string'},
'transcript': {'nullable': True,
'title': 'Transcript',
'type': 'string'}},
'title': 'Output',
'type': 'object'}