Adding temperature scaling on Joiner logits: (#789)
* Adding temperature scaling on Joiner logits:
- T hard-coded to 2.0
- so far best result NCE 0.122 (still not so high)
- the BPE scores were rescaled with 0.2 (but then also incorrect words
get high confidence, visually reasonable histograms are for 0.5 scale)
- BPE->WORD score merging done by min(.) function
(tried also prob-product, and also arithmetic, geometric, harmonic mean)
- without temperature scaling (i.e. scale 1.0), the best NCE was 0.032 (here product merging was best)
Results seem consistent with: https://arxiv.org/abs/2110.15222
Everything tuned on a very-small set of 100 sentences with 813 words and 10.2% WER, a Czech model.
I also experimented with blank posteriors mixed into the BPE confidences,
but no NCE improvement found, so not pushing that.
Temperature scling added also to the Greedy search confidences.
* making `temperature_scale` configurable from outside
This commit is contained in:
@@ -96,16 +96,23 @@ struct OnlineRecognizerConfig {
|
||||
|
||||
float blank_penalty = 0.0;
|
||||
|
||||
float temperature_scale = 2.0;
|
||||
|
||||
OnlineRecognizerConfig() = default;
|
||||
|
||||
OnlineRecognizerConfig(
|
||||
const FeatureExtractorConfig &feat_config,
|
||||
const OnlineModelConfig &model_config, const OnlineLMConfig &lm_config,
|
||||
const OnlineModelConfig &model_config,
|
||||
const OnlineLMConfig &lm_config,
|
||||
const EndpointConfig &endpoint_config,
|
||||
const OnlineCtcFstDecoderConfig &ctc_fst_decoder_config,
|
||||
bool enable_endpoint, const std::string &decoding_method,
|
||||
int32_t max_active_paths, const std::string &hotwords_file,
|
||||
float hotwords_score, float blank_penalty)
|
||||
bool enable_endpoint,
|
||||
const std::string &decoding_method,
|
||||
int32_t max_active_paths,
|
||||
const std::string &hotwords_file,
|
||||
float hotwords_score,
|
||||
float blank_penalty,
|
||||
float temperature_scale)
|
||||
: feat_config(feat_config),
|
||||
model_config(model_config),
|
||||
lm_config(lm_config),
|
||||
@@ -114,9 +121,10 @@ struct OnlineRecognizerConfig {
|
||||
enable_endpoint(enable_endpoint),
|
||||
decoding_method(decoding_method),
|
||||
max_active_paths(max_active_paths),
|
||||
hotwords_score(hotwords_score),
|
||||
hotwords_file(hotwords_file),
|
||||
blank_penalty(blank_penalty) {}
|
||||
hotwords_score(hotwords_score),
|
||||
blank_penalty(blank_penalty),
|
||||
temperature_scale(temperature_scale) {}
|
||||
|
||||
void Register(ParseOptions *po);
|
||||
bool Validate() const;
|
||||
|
||||
Reference in New Issue
Block a user