Hugging Face's logo

qualcomm
/
Whisper-Small-V2

Other
PyTorch
deprecated
Model card Files
xet
Community
qaihm-bot commited on
Commit
1537b42
·
verified ·
1 Parent(s): 1f47a5a

v0.34.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.34.0 for changelog.

Files changed (14) hide show
  1. README.md +2 -20
  2. precompiled/qualcomm-qcs8275-proxy/sdk_versions.yml +3 -0
  3. precompiled/qualcomm-qcs8450-proxy/sdk_versions.yml +3 -0
  4. precompiled/qualcomm-qcs8550-proxy/sdk_versions.yml +3 -0
  5. precompiled/qualcomm-qcs9075-proxy/sdk_versions.yml +3 -0
  6. precompiled/qualcomm-sa7255p/sdk_versions.yml +3 -0
  7. precompiled/qualcomm-sa8255p-proxy/sdk_versions.yml +3 -0
  8. precompiled/qualcomm-sa8295p/sdk_versions.yml +3 -0
  9. precompiled/qualcomm-sa8650p-proxy/sdk_versions.yml +3 -0
  10. precompiled/qualcomm-sa8775p/sdk_versions.yml +3 -0
  11. precompiled/qualcomm-snapdragon-8-elite/sdk_versions.yml +5 -0
  12. precompiled/qualcomm-snapdragon-8gen2/sdk_versions.yml +5 -0
  13. precompiled/qualcomm-snapdragon-8gen3/sdk_versions.yml +5 -0
  14. precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml +5 -0
README.md CHANGED
@@ -24,6 +24,7 @@ More details on model performance across various devices, can be found
24
  [here](https://aihub.qualcomm.com/models/whisper_small_v2).
25
 
26
 
 
27
  ### Model Details
28
 
29
  - **Model Type:** Model_use_case.speech_recognition
@@ -125,26 +126,7 @@ device. This script does the following:
125
  ```bash
126
  python -m qai_hub_models.models.whisper_small_v2.export
127
  ```
128
- ```
129
- Profiling Results
130
- ------------------------------------------------------------
131
- HfWhisperEncoder
132
- Device : cs_8275 (ANDROID 14)
133
- Runtime : QNN_CONTEXT_BINARY
134
- Estimated inference time (ms) : 426.9
135
- Estimated peak memory usage (MB): [0, 9]
136
- Total # Ops : 1606
137
- Compute Unit(s) : npu (1606 ops) gpu (0 ops) cpu (0 ops)
138
-
139
- ------------------------------------------------------------
140
- HfWhisperDecoder
141
- Device : cs_8275 (ANDROID 14)
142
- Runtime : QNN_CONTEXT_BINARY
143
- Estimated inference time (ms) : 17.6
144
- Estimated peak memory usage (MB): [47, 55]
145
- Total # Ops : 2302
146
- Compute Unit(s) : npu (2302 ops) gpu (0 ops) cpu (0 ops)
147
- ```
148
 
149
 
150
  ## How does this work?
 
24
  [here](https://aihub.qualcomm.com/models/whisper_small_v2).
25
 
26
 
27
+
28
  ### Model Details
29
 
30
  - **Model Type:** Model_use_case.speech_recognition
 
126
  ```bash
127
  python -m qai_hub_models.models.whisper_small_v2.export
128
  ```
129
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
130
 
131
 
132
  ## How does this work?
precompiled/qualcomm-qcs8275-proxy/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-qcs8450-proxy/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-qcs8550-proxy/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-qcs9075-proxy/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-sa7255p/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-sa8255p-proxy/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-sa8295p/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-sa8650p-proxy/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-sa8775p/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-snapdragon-8-elite/sdk_versions.yml ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
4
+ precompiled_qnn_onnx:
5
+ qairt: 2.33.2.250410134701_117956
precompiled/qualcomm-snapdragon-8gen2/sdk_versions.yml ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
4
+ precompiled_qnn_onnx:
5
+ qairt: 2.33.2.250410134701_117956
precompiled/qualcomm-snapdragon-8gen3/sdk_versions.yml ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
4
+ precompiled_qnn_onnx:
5
+ qairt: 2.33.2.250410134701_117956
precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
4
+ precompiled_qnn_onnx:
5
+ qairt: 2.33.2.250410134701_117956