Hugging Face's logo

qualcomm
/
Whisper-Small-En

Automatic Speech Recognition
PyTorch
LiteRT
foundation
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
d666d84
·
verified ·
1 Parent(s): 9a356b7

v0.29.1

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.29.1 for changelog.

Files changed (12) hide show
  1. README.md +25 -29
  2. WhisperDecoder.bin → Whisper-Small-En_WhisperDecoderInf.onnx +2 -2
  3. WhisperDecoder.onnx → Whisper-Small-En_WhisperDecoderInf.tflite +2 -2
  4. WhisperEncoderInf.onnx → Whisper-Small-En_WhisperEncoderInf.onnx +0 -0
  5. WhisperEncoder.tflite → Whisper-Small-En_WhisperEncoderInf.tflite +0 -0
  6. WhisperDecoder.so +0 -3
  7. WhisperDecoder.tflite +0 -3
  8. WhisperDecoderInf.tflite +0 -3
  9. WhisperEncoder.bin +0 -3
  10. WhisperEncoder.onnx +0 -3
  11. WhisperEncoder.so +0 -3
  12. WhisperEncoderInf.tflite +0 -3
README.md CHANGED
@@ -38,32 +38,28 @@ More details on model performance across various devices, can be found
38
 
39
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
40
  |---|---|---|---|---|---|---|---|---|
41
- | WhisperEncoderInf | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 3226.414 ms | 108 - 141 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
42
- | WhisperEncoderInf | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 986.224 ms | 101 - 200 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
43
- | WhisperEncoderInf | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1103.354 ms | 74 - 155 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
44
- | WhisperEncoderInf | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 1271.289 ms | 100 - 133 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
45
- | WhisperEncoderInf | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 3226.414 ms | 108 - 141 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
46
- | WhisperEncoderInf | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 779.384 ms | 24 - 121 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
47
- | WhisperEncoderInf | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 656.617 ms | 109 - 142 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
48
- | WhisperEncoderInf | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 699.122 ms | 110 - 183 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
49
- | WhisperEncoderInf | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 1271.289 ms | 100 - 133 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
50
- | WhisperEncoderInf | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 1245.355 ms | 0 - 164 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
51
- | WhisperEncoderInf | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 525.323 ms | 110 - 200 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
52
- | WhisperEncoderInf | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 542.231 ms | 111 - 141 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
53
- | WhisperEncoderInf | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 609.485 ms | 295 - 295 MB | NPU | [Whisper-Small-En.onnx](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.onnx) |
54
- | WhisperDecoderInf | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 65.318 ms | 16 - 268 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
55
- | WhisperDecoderInf | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 62.718 ms | 16 - 404 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
56
- | WhisperDecoderInf | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 55.629 ms | 16 - 43 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
57
- | WhisperDecoderInf | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 52.514 ms | 16 - 268 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
58
- | WhisperDecoderInf | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 65.318 ms | 16 - 268 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
59
- | WhisperDecoderInf | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 54.617 ms | 16 - 44 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
60
- | WhisperDecoderInf | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 56.316 ms | 16 - 248 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
61
- | WhisperDecoderInf | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 55.232 ms | 14 - 40 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
62
- | WhisperDecoderInf | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 52.514 ms | 16 - 268 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
63
- | WhisperDecoderInf | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 55.786 ms | 16 - 45 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
64
- | WhisperDecoderInf | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 45.752 ms | 16 - 412 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
65
- | WhisperDecoderInf | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 42.151 ms | 23 - 278 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
66
- | WhisperDecoderInf | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 48.51 ms | 226 - 226 MB | NPU | [Whisper-Small-En.onnx](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.onnx) |
67
 
68
 
69
 
@@ -127,8 +123,8 @@ Profiling Results
127
  WhisperEncoderInf
128
  Device : cs_8275 (ANDROID 14)
129
  Runtime : TFLITE
130
- Estimated inference time (ms) : 3226.4
131
- Estimated peak memory usage (MB): [108, 141]
132
  Total # Ops : 911
133
  Compute Unit(s) : npu (0 ops) gpu (900 ops) cpu (11 ops)
134
 
@@ -136,7 +132,7 @@ Compute Unit(s) : npu (0 ops) gpu (900 ops) cpu (11 ops)
136
  WhisperDecoderInf
137
  Device : cs_8275 (ANDROID 14)
138
  Runtime : TFLITE
139
- Estimated inference time (ms) : 65.3
140
  Estimated peak memory usage (MB): [16, 268]
141
  Total # Ops : 2573
142
  Compute Unit(s) : npu (2573 ops) gpu (0 ops) cpu (0 ops)
 
38
 
39
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
40
  |---|---|---|---|---|---|---|---|---|
41
+ | WhisperEncoderInf | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 3224.417 ms | 107 - 140 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
42
+ | WhisperEncoderInf | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 1638.428 ms | 109 - 208 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
43
+ | WhisperEncoderInf | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 688.683 ms | 110 - 143 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
44
+ | WhisperEncoderInf | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 3224.417 ms | 107 - 140 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
45
+ | WhisperEncoderInf | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 897.319 ms | 100 - 123 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
46
+ | WhisperEncoderInf | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 656.478 ms | 109 - 140 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
47
+ | WhisperEncoderInf | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 685.162 ms | 18 - 181 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
48
+ | WhisperEncoderInf | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 817.059 ms | 104 - 147 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
49
+ | WhisperEncoderInf | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 524.574 ms | 109 - 203 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
50
+ | WhisperEncoderInf | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 543.977 ms | 110 - 141 MB | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
51
+ | WhisperEncoderInf | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 607.169 ms | 295 - 295 MB | NPU | [Whisper-Small-En.onnx](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.onnx) |
52
+ | WhisperDecoderInf | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 64.601 ms | 16 - 268 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
53
+ | WhisperDecoderInf | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 61.873 ms | 16 - 405 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
54
+ | WhisperDecoderInf | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 54.727 ms | 12 - 40 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
55
+ | WhisperDecoderInf | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 64.601 ms | 16 - 268 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
56
+ | WhisperDecoderInf | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 55.594 ms | 16 - 42 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
57
+ | WhisperDecoderInf | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 56.165 ms | 16 - 248 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
58
+ | WhisperDecoderInf | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 55.696 ms | 16 - 42 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
59
+ | WhisperDecoderInf | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 55.186 ms | 16 - 44 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
60
+ | WhisperDecoderInf | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 44.815 ms | 14 - 417 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
61
+ | WhisperDecoderInf | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 40.741 ms | 15 - 270 MB | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.tflite) |
62
+ | WhisperDecoderInf | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 46.9 ms | 227 - 227 MB | NPU | [Whisper-Small-En.onnx](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/Whisper-Small-En.onnx) |
 
 
 
 
63
 
64
 
65
 
 
123
  WhisperEncoderInf
124
  Device : cs_8275 (ANDROID 14)
125
  Runtime : TFLITE
126
+ Estimated inference time (ms) : 3224.4
127
+ Estimated peak memory usage (MB): [107, 140]
128
  Total # Ops : 911
129
  Compute Unit(s) : npu (0 ops) gpu (900 ops) cpu (11 ops)
130
 
 
132
  WhisperDecoderInf
133
  Device : cs_8275 (ANDROID 14)
134
  Runtime : TFLITE
135
+ Estimated inference time (ms) : 64.6
136
  Estimated peak memory usage (MB): [16, 268]
137
  Total # Ops : 2573
138
  Compute Unit(s) : npu (2573 ops) gpu (0 ops) cpu (0 ops)
WhisperDecoder.bin → Whisper-Small-En_WhisperDecoderInf.onnx RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8d21bff6c9f5b03426aff602f5fa129388bc9e4d46d61cd545436d506ab601d
3
- size 362568216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1f595d19ce40056d5531b9accf21826016a84ee02e03b3c03c7ba0da0831af9
3
+ size 716944574
WhisperDecoder.onnx → Whisper-Small-En_WhisperDecoderInf.tflite RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da5c0240acf3e45c02a027aebe76e15f379780f14b103176c7f00c5d0a16f4d1
3
- size 717076364
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c2049a24dbe4c1fcdc354b12d15e1bfad705f70316febd095f8f67c81745fe8
3
+ size 557615568
WhisperEncoderInf.onnx → Whisper-Small-En_WhisperEncoderInf.onnx RENAMED
File without changes
WhisperEncoder.tflite → Whisper-Small-En_WhisperEncoderInf.tflite RENAMED
File without changes
WhisperDecoder.so DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:55d7f7466acec5afdde4b61d906b41857512de8a63c31ed1b50ce7ae18205ea1
3
- size 361676272
 
 
 
 
WhisperDecoder.tflite DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a612f76581dfd7caadf1a563bb55ef962fad57d8c16be08508d0958027aee2d7
3
- size 557617160
 
 
 
 
WhisperDecoderInf.tflite DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:89313eac23258eca02ba4afe875971b5742cda08f95f2c4c4d0b77daa5d500b8
3
- size 557616808
 
 
 
 
WhisperEncoder.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:40c88b5954377b3682db6bb46453757b46d6ef12e11af2421c4ab6de703647ab
3
- size 248188072
 
 
 
 
WhisperEncoder.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f001457af241e0b37311a585a59cdcbdb1646049f28c259a26fe021b682a0985
3
- size 409498271
 
 
 
 
WhisperEncoder.so DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2e56d11e4b3197aa5b13f4f2b4f343b06d762772ec284a3b60ce09a26b28e9a
3
- size 207519296
 
 
 
 
WhisperEncoderInf.tflite DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d63084276fa4f2d937797dc9447ef67c8f18814b04848171dac47ad54eeab3a
3
- size 409468768